Console log: 'Microsoft.ML.Predictor.Tests' from job 5a35f47e-ea76-444d-850a-5f9402ad78be (ubuntu.2204.armarch.open) using docker image mcr.microsoft.com/dotnet-buildtools/prereqs:ubuntu-22.04-helix-arm64v8 on a005EXM running $HELIX_CORRELATION_PAYLOAD/scripts/6c7ac47073c942e5aaa9740e0a0f140e/execute.sh in /datadisks/disk1/work/ACCE097F/w/B4B60A24/e max 3600 seconds Output: [BEGIN EXECUTION] + cd /root/helix/work/workitem/e + mkdir -p /datadisks/disk1/dumps/ + /root/helix/work/correlation/scripts/6c7ac47073c942e5aaa9740e0a0f140e/execute.sh + export ML_TEST_DATADIR=/root/helix/work/correlation + export MICROSOFTML_RESOURCE_PATH=/root/helix/work/workitem/e + sudo chmod -R 777 /root/helix/work/workitem/e + sudo chown -R /root/helix/work/workitem/e chown: missing operand after ‘/root/helix/work/workitem/e’ Try 'chown --help' for more information. + export PATH=/root/helix/work/correlation/dotnet-cli:/home/helixbot/.vsts-env/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin + sudo apt update WARNING: apt does not have a stable CLI interface. Use with caution in scripts. Get:1 https://packages.microsoft.com/ubuntu/22.04/prod jammy InRelease [3,632 B] Get:2 https://packages.microsoft.com/ubuntu/22.04/prod jammy/main all Packages [1,331 B] Get:3 https://packages.microsoft.com/ubuntu/22.04/prod jammy/main arm64 Packages [525 kB] Get:4 http://ports.ubuntu.com/ubuntu-ports jammy InRelease [270 kB] Get:5 http://ports.ubuntu.com/ubuntu-ports jammy-updates InRelease [128 kB] Get:6 http://ports.ubuntu.com/ubuntu-ports jammy-backports InRelease [127 kB] Get:7 http://ports.ubuntu.com/ubuntu-ports jammy-security InRelease [129 kB] Get:8 http://ports.ubuntu.com/ubuntu-ports jammy/main arm64 Packages [1,758 kB] Get:9 http://ports.ubuntu.com/ubuntu-ports jammy/multiverse arm64 Packages [224 kB] Get:10 http://ports.ubuntu.com/ubuntu-ports jammy/restricted arm64 Packages [24.2 kB] Get:11 http://ports.ubuntu.com/ubuntu-ports jammy/universe arm64 Packages [17.2 MB] Get:12 http://ports.ubuntu.com/ubuntu-ports jammy-updates/restricted arm64 Packages [8,100 kB] Get:13 http://ports.ubuntu.com/ubuntu-ports jammy-updates/universe arm64 Packages [1,704 kB] Get:14 http://ports.ubuntu.com/ubuntu-ports jammy-updates/multiverse arm64 Packages [70.2 kB] Get:15 http://ports.ubuntu.com/ubuntu-ports jammy-updates/main arm64 Packages [4,438 kB] Get:16 http://ports.ubuntu.com/ubuntu-ports jammy-backports/universe arm64 Packages [33.7 kB] Get:17 http://ports.ubuntu.com/ubuntu-ports jammy-backports/main arm64 Packages [82.5 kB] Get:18 http://ports.ubuntu.com/ubuntu-ports jammy-security/multiverse arm64 Packages [63.4 kB] Get:19 http://ports.ubuntu.com/ubuntu-ports jammy-security/universe arm64 Packages [1,408 kB] Get:20 http://ports.ubuntu.com/ubuntu-ports jammy-security/main arm64 Packages [4,121 kB] Get:21 http://ports.ubuntu.com/ubuntu-ports jammy-security/restricted arm64 Packages [7,798 kB] Fetched 48.2 MB in 3s (16.5 MB/s) Reading package lists... Building dependency tree... Reading state information... W: https://packages.microsoft.com/ubuntu/22.04/prod/dists/jammy/InRelease: Key is stored in legacy trusted.gpg keyring (/etc/apt/trusted.gpg), see the DEPRECATION section in apt-key(8) for details. 3 packages can be upgraded. Run 'apt list --upgradable' to see them. + sudo apt-get install libomp-dev libomp5 -y Reading package lists... Building dependency tree... Reading state information... The following additional packages will be installed: libomp-14-dev libomp5-14 Suggested packages: libomp-14-doc The following NEW packages will be installed: libomp-14-dev libomp-dev libomp5 libomp5-14 0 upgraded, 4 newly installed, 0 to remove and 3 not upgraded. Need to get 677 kB of archives. After this operation, 9,071 kB of additional disk space will be used. Get:1 http://ports.ubuntu.com/ubuntu-ports jammy-updates/universe arm64 libomp5-14 arm64 1:14.0.0-1ubuntu1.1 [337 kB] Get:2 http://ports.ubuntu.com/ubuntu-ports jammy-updates/universe arm64 libomp-14-dev arm64 1:14.0.0-1ubuntu1.1 [334 kB] Get:3 http://ports.ubuntu.com/ubuntu-ports jammy/universe arm64 libomp-dev arm64 1:14.0-55~exp2 [3,074 B] Get:4 http://ports.ubuntu.com/ubuntu-ports jammy/universe arm64 libomp5 arm64 1:14.0-55~exp2 [3,060 B] debconf: delaying package configuration, since apt-utils is not installed Fetched 677 kB in 1s (728 kB/s) Selecting previously unselected package libomp5-14:arm64. (Reading database ... (Reading database ... 5% (Reading database ... 10% (Reading database ... 15% (Reading database ... 20% (Reading database ... 25% (Reading database ... 30% (Reading database ... 35% (Reading database ... 40% (Reading database ... 45% (Reading database ... 50% (Reading database ... 55% (Reading database ... 60% (Reading database ... 65% (Reading database ... 70% (Reading database ... 75% (Reading database ... 80% (Reading database ... 85% (Reading database ... 90% (Reading database ... 95% (Reading database ... 100% (Reading database ... 41924 files and directories currently installed.) Preparing to unpack .../libomp5-14_1%3a14.0.0-1ubuntu1.1_arm64.deb ... Unpacking libomp5-14:arm64 (1:14.0.0-1ubuntu1.1) ... Selecting previously unselected package libomp-14-dev. Preparing to unpack .../libomp-14-dev_1%3a14.0.0-1ubuntu1.1_arm64.deb ... Unpacking libomp-14-dev (1:14.0.0-1ubuntu1.1) ... Selecting previously unselected package libomp-dev:arm64. Preparing to unpack .../libomp-dev_1%3a14.0-55~exp2_arm64.deb ... Unpacking libomp-dev:arm64 (1:14.0-55~exp2) ... Selecting previously unselected package libomp5:arm64. Preparing to unpack .../libomp5_1%3a14.0-55~exp2_arm64.deb ... Unpacking libomp5:arm64 (1:14.0-55~exp2) ... Setting up libomp5-14:arm64 (1:14.0.0-1ubuntu1.1) ... Setting up libomp5:arm64 (1:14.0-55~exp2) ... Setting up libomp-14-dev (1:14.0.0-1ubuntu1.1) ... Setting up libomp-dev:arm64 (1:14.0-55~exp2) ... Processing triggers for libc-bin (2.35-0ubuntu3.15) ... + ./runTests.sh ----- start Mon Sep 21 01:02:33 PM UTC 2026 =============== To repro directly: ===================================================== pushd . dotnet exec --roll-forward Major --runtimeconfig Microsoft.ML.Predictor.Tests.runtimeconfig.json --depsfile Microsoft.ML.Predictor.Tests.deps.json /root/helix/work/correlation/xunit-runner/tools/netcoreapp2.0/xunit.console.dll Microsoft.ML.Predictor.Tests.dll -notrait Category=SkipInCI -xml testResults.xml popd =========================================================================================================== /root/helix/work/workitem/e /root/helix/work/workitem/e xUnit.net Console Runner v2.9.3+9712244020 (64-bit .NET 8.0.16)  Discovering: Microsoft.ML.Predictor.Tests (method display = ClassAndMethod, method display options = None)  Discovered: Microsoft.ML.Predictor.Tests (found 112 test cases)  Starting: Microsoft.ML.Predictor.Tests (parallel test collections = on [2 threads], stop on fail = off) Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLDSvmNoBiasTest  Microsoft.ML.RunTests.Global.AssertHandlerTest [SKIP]  Disabled Starting test: Microsoft.ML.RunTests.TestGamPublicInterfaces.TestGamDirectInstantiation  Microsoft.ML.RunTests.TestParallelFasttreeInterface.CheckFastTreeParallelInterface [SKIP]  'checker' is not a valid value for the 'parag' argument in FastTree  Microsoft.ML.RunTests.TestConcurrency.TestCVWithLRParallel [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestConcurrency.TestBootstrapWithLRParallel [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestGamPublicInterfaces.TestGamDirectInstantiation with memory usage 153,309,184.00 and max memory usage 153,309,184.00 Starting test: Microsoft.ML.RunTests.TestTransposer.TransposerTest Finished test: Microsoft.ML.RunTests.TestTransposer.TransposerTest with memory usage 172,089,344.00 and max memory usage 172,089,344.00  Microsoft.ML.RunTests.TestTransposer.TransposerTest [PASS]  Output:  Test TransposerTest: aborted: passed Starting test: Microsoft.ML.RunTests.TestTransposer.TransposerSaverLoaderTest Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLDSvmNoBiasTest with memory usage 177,709,056.00 and max memory usage 177,709,056.00 Starting test: Microsoft.ML.RunTests.TestPredictors.PAVCalibratorLinearSvmTest  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLDSvmNoBiasTest [FAIL]  Assert.Equal() Failure: Values differ  Expected: 0  Actual: 4  Stack Trace:  /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs(221,0): at Microsoft.ML.RunTests.BaseTestBaseline.Done()  /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs(2173,0): at Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLDSvmNoBiasTest()  at System.RuntimeMethodHandle.InvokeMethod(Object target, Void** arguments, Signature sig, Boolean isConstructor)  at System.Reflection.MethodBaseInvoker.InvokeWithNoArgs(Object obj, BindingFlags invokeAttr)  Output:  Running 'LdSvm' on 'breast-cancer'  Running as: TrainTest tr=LdSvm{iter=1000 bias=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=LdSvm{iter=1000 bias=-} dout=/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 16 rows with missing feature/label values    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 216 | 23 | 0.9038    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9558 | 0.9497 |    OVERALL 0/1 ACCURACY: 0.951684    LOG LOSS/instance: 0.251640    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.730579    AUC: 0.969024      OVERALL RESULTS    ---------------------------------------    AUC: 0.969024 (0.0000)    Accuracy: 0.951684 (0.0000)    Positive precision: 0.955752 (0.0000)    Positive recall: 0.903766 (0.0000)    Negative precision: 0.949672 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.251640 (0.0000)    Log-loss reduction: 0.730579 (0.0000)    F1 Score: 0.929032 (0.0000)    AUPRC: 0.965033 (0.0000)      ---------------------------------------    Physical memory usage(MB): 152    Virtual memory usage(MB): 266784    09/21/2026 13:02:34 PM Time elapsed(s): 1.031      Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-nob-TrainTest-breast-cancer-out.txt  Output matches baseline: 'LdSvm/LDSVM-nob-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-nob-TrainTest-breast-cancer-rp.txt  *** Failure #1: Values to compare are 0.91129 and 0.955752  AllowedVariance: 0.01  delta: -0.05  delta2: -0.04   Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CompareNumbersWithTolerance(Double, Double, System.Nullable`1[System.Int32], Int32, Boolean) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 663  Boolean MatchNumberWithTolerance(System.Text.RegularExpressions.MatchCollection, System.Text.RegularExpressions.MatchCollection, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 615  Boolean GetNumbersFromFile(System.String ByRef, System.String ByRef, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 581  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 556  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_TrainTest(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Boolean, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 399  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 365  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void BinaryClassifierLDSvmNoBiasTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 2172  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  *** Failure #2: Output and baseline mismatch at line 3, expected '0.971682 0.948755 0.91129 0.945607 0.970115 0.95045 0.259132 0.722558 0.928131 0.961861 - 1000 LdSvm %Data% %Data% %Output% 99 0 0 maml.exe TrainTest test=%Data% tr=LdSvm{iter=1000 bias=-} dout=%Output% data=%Data% out=%Output% seed=1 /bias:-;/iter:1000 ' but got '0.969024 0.951684 0.955752 0.903766 0.949672 0.977477 0.25164 0.730579 0.929032 0.965033 - 1000 LdSvm %Data% %Data% %Output% 99 0 0 maml.exe TrainTest test=%Data% tr=LdSvm{iter=1000 bias=-} dout=%Output% data=%Data% out=%Output% seed=1 /bias:-;/iter:1000 ' : 'LdSvm/LDSVM-nob-TrainTest-breast-cancer-rp.txt'  Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 566  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_TrainTest(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Boolean, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 399  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 365  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void BinaryClassifierLDSvmNoBiasTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 2172  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-nob-TrainTest-breast-cancer.txt  Output matches baseline: 'LdSvm/LDSVM-nob-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 216 | 23 | 0.9038    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9558 | 0.9497 |    OVERALL 0/1 ACCURACY: 0.951684    LOG LOSS/instance: 0.251640    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.730579    AUC: 0.969024      OVERALL RESULTS    ---------------------------------------    AUC: 0.969024 (0.0000)    Accuracy: 0.951684 (0.0000)    Positive precision: 0.955752 (0.0000)    Positive recall: 0.903766 (0.0000)    Negative precision: 0.949672 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.251640 (0.0000)    Log-loss reduction: 0.730579 (0.0000)    F1 Score: 0.929032 (0.0000)    AUPRC: 0.965033 (0.0000)      ---------------------------------------    Physical memory usage(MB): 156    Virtual memory usage(MB): 266784    09/21/2026 13:02:35 PM Time elapsed(s): 0.037      Suffix of length 34 compared against sequence of length 38  Running 'LdSvm' on 'breast-cancer'  Running as: CV tr=LdSvm{iter=1000 bias=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-CV-breast-cancer.txt} threads-  maml.exe CV tr=LdSvm{iter=1000 bias=-} threads=- dout=/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 8 rows with missing feature/label values    Training calibrator.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 8 rows with missing feature/label values    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 126 | 8 | 0.9403    negative || 12 | 208 | 0.9455    ||======================    Precision || 0.9130 | 0.9630 |    OVERALL 0/1 ACCURACY: 0.943503    LOG LOSS/instance: 0.262484    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.725722    AUC: 0.980801    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 103 | 2 | 0.9810    negative || 36 | 188 | 0.8393    ||======================    Precision || 0.7410 | 0.9895 |    OVERALL 0/1 ACCURACY: 0.884498    LOG LOSS/instance: 0.231456    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.743810    AUC: 0.984396      OVERALL RESULTS    ---------------------------------------    AUC: 0.982598 (0.0018)    Accuracy: 0.914001 (0.0295)    Positive precision: 0.827025 (0.0860)    Positive recall: 0.960625 (0.0203)    Negative precision: 0.976218 (0.0133)    Negative recall: 0.892370 (0.0531)    Log-loss: 0.246970 (0.0155)    Log-loss reduction: 0.734766 (0.0090)    F1 Score: 0.885366 (0.0411)    AUPRC: 0.972638 (0.0101)      ---------------------------------------    Physical memory usage(MB): 169    Virtual memory usage(MB): 266786    09/21/2026 13:02:36 PM Time elapsed(s): 0.93      Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-nob-CV-breast-cancer-out.txt  Output matches baseline: 'LdSvm/LDSVM-nob-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-nob-CV-breast-cancer-rp.txt  *** Failure #3: Values to compare are 0.892063 and 0.914001  AllowedVariance: 0.01  delta: -0.02  delta2: -0.02   Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CompareNumbersWithTolerance(Double, Double, System.Nullable`1[System.Int32], Int32, Boolean) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 663  Boolean MatchNumberWithTolerance(System.Text.RegularExpressions.MatchCollection, System.Text.RegularExpressions.MatchCollection, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 615  Boolean GetNumbersFromFile(System.String ByRef, System.String ByRef, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 581  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 556  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_CV(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 445  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 366  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void BinaryClassifierLDSvmNoBiasTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 2172  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  *** Failure #4: Output and baseline mismatch at line 3, expected '0.977455 0.892063 0.790637 0.954193 0.971537 0.863149 0.245954 0.738663 0.859972 0.964976 - 1000 LdSvm %Data% %Output% 99 0 0 maml.exe CV tr=LdSvm{iter=1000 bias=-} threads=- dout=%Output% data=%Data% seed=1 /bias:-;/iter:1000 ' but got '0.982598 0.914001 0.827025 0.960625 0.976218 0.89237 0.24697 0.734766 0.885366 0.972638 - 1000 LdSvm %Data% %Output% 99 0 0 maml.exe CV tr=LdSvm{iter=1000 bias=-} threads=- dout=%Output% data=%Data% seed=1 /bias:-;/iter:1000 ' : 'LdSvm/LDSVM-nob-CV-breast-cancer-rp.txt'  Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 566  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_CV(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 445  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 366  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void BinaryClassifierLDSvmNoBiasTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 2172  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-nob-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-nob-CV-breast-cancer.txt  Output matches baseline: 'LdSvm/LDSVM-nob-CV-breast-cancer.txt'  Test BinaryClassifierLDSvmNoBiasTest: completed normally: failed  Test BinaryClassifierLDSvmNoBiasTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestTransposer.TransposerSaverLoaderTest with memory usage 185,044,992.00 and max memory usage 185,044,992.00  Microsoft.ML.RunTests.TestTransposer.TransposerSaverLoaderTest [PASS]  Output:  Wrote row-wise data, schema, and metadata data view in 440926 bytes   Starting test: Microsoft.ML.RunTests.TestIniModels.TestGamRegressionIni  Wrote A data view in 60607 bytes    Wrote B data view in 364868 bytes    Wrote C data view in 6491 bytes    Wrote D data view in 11587 bytes    Wrote E data view in 1036 bytes    Wrote F data view in 3875 bytes    Test TransposerSaverLoaderTest: completed normally: passed Finished test: Microsoft.ML.RunTests.TestPredictors.PAVCalibratorLinearSvmTest with memory usage 192,966,656.00 and max memory usage 192,966,656.00  Microsoft.ML.RunTests.TestPredictors.PAVCalibratorLinearSvmTest [PASS]  Output:  Running 'LinearSVM' on 'breast-cancer'  Running as: TrainTest tr=LinearSVM{iter=100 lambda=0.03} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration-model.zip} dout={/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration.txt} cali=PAV  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=LinearSVM{iter=100 lambda=0.03} cali=PAV dout=/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 1600 instances with missing features during training (over 100 iterations; 16 inst/iter)    Training calibrator.    PAV calibrator: piecewise function approximation has 8 components.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 226 | 13 | 0.9456    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9617 | 0.9710 |    OVERALL 0/1 ACCURACY: 0.967789    LOG LOSS/instance: 0.084588    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.909435    AUC: 0.995797      OVERALL RESULTS    ---------------------------------------    AUC: 0.995797 (0.0000)    Accuracy: 0.967789 (0.0000)    Positive precision: 0.961702 (0.0000)    Positive recall: 0.945607 (0.0000)    Negative precision: 0.970982 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.084588 (0.0000)    Log-loss reduction: 0.909435 (0.0000)    F1 Score: 0.953586 (0.0000)    AUPRC: 0.991453 (0.0000)      ---------------------------------------    Physical memory usage(MB): 176    Virtual memory usage(MB): 266794    09/21/2026 13:02:36 PM Time elapsed(s): 0.197      Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration-out.txt  Output matches baseline: 'LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration-rp.txt  Output matches baseline: 'LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration.txt  Output matches baseline: 'LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.PAVcalibration-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 226 | 13 | 0.9456    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9617 | 0.9710 |    OVERALL 0/1 ACCURACY: 0.967789    LOG LOSS/instance: 0.084588    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.909435    AUC: 0.995797      OVERALL RESULTS    ---------------------------------------    AUC: 0.995797 (0.0000)    Accuracy: 0.967789 (0.0000)    Positive precision: 0.961702 (0.0000)    Positive recall: 0.945607 (0.0000)    Negative precision: 0.970982 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.084588 (0.0000)    Log-loss reduction: 0.909435 (0.0000)    F1 Score: 0.953586 (0.0000)    AUPRC: 0.991453 (0.0000)      ---------------------------------------    Physical memory usage(MB): 176    Virtual memory usage(MB): 266794    09/21/2026 13:02:36 PM Time elapsed(s): 0.029      Suffix of length 34 compared against sequence of length 39  Running 'LinearSVM' on 'breast-cancer'  Running as: CV tr=LinearSVM{iter=100 lambda=0.03} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration.txt} threads- cali=PAV  maml.exe CV tr=LinearSVM{iter=100 lambda=0.03} threads=- cali=PAV dout=/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 800 instances with missing features during training (over 100 iterations; 8 inst/iter)    Training calibrator.    PAV calibrator: piecewise function approximation has 6 components.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.   Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesBestDiverseSelectorTest  Warning:  Skipped 800 instances with missing features during training (over 100 iterations; 8 inst/iter)    Training calibrator.    PAV calibrator: piecewise function approximation has 6 components.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 128 | 6 | 0.9552    negative || 7 | 213 | 0.9682    ||======================    Precision || 0.9481 | 0.9726 |    OVERALL 0/1 ACCURACY: 0.963277    LOG LOSS/instance: Infinity    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): -Infinity    AUC: 0.994233    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 97 | 8 | 0.9238    negative || 2 | 222 | 0.9911    ||======================    Precision || 0.9798 | 0.9652 |    OVERALL 0/1 ACCURACY: 0.969605    LOG LOSS/instance: 0.220291    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.756168    AUC: 0.997491      OVERALL RESULTS    ---------------------------------------    AUC: 0.995862 (0.0016)    Accuracy: 0.966441 (0.0032)    Positive precision: 0.963973 (0.0158)    Positive recall: 0.939517 (0.0157)    Negative precision: 0.968910 (0.0037)    Negative recall: 0.979627 (0.0114)    Log-loss: Infinity (NaN)    Log-loss reduction: -Infinity (NaN)    F1 Score: 0.951327 (0.0003)    AUPRC: 0.991949 (0.0025)      ---------------------------------------    Physical memory usage(MB): 184    Virtual memory usage(MB): 266794    09/21/2026 13:02:36 PM Time elapsed(s): 0.167      Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration-out.txt  Output matches baseline: 'LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration-rp.txt  Output matches baseline: 'LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration.txt  Output matches baseline: 'LinearSVM/LinearSVM-CV-breast-cancer.PAVcalibration.txt'  Test PAVCalibratorLinearSvmTest: completed normally: passed  Microsoft.ML.RunTests.TestPredictors.LightGBMPreviousModelBaselineTest [SKIP]  LightGBM is 64-bit only  Microsoft.ML.RunTests.TestPredictors.RegressorSdcaTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierSymSgdTest [SKIP]  This test requires a native library SymSgdNative that wasn't found. Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesBestDiverseSelectorTest with memory usage 193,822,720.00 and max memory usage 193,822,720.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesBestDiverseSelectorTest [PASS]  Output:  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{nm=20 pt=BestDiverseSelector tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{nm=20 pt=BestDiverseSelector tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 1 of 20 finished in 00:00:00.0155509    Beginning training model 2 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 2 of 20 finished in 00:00:00.0037886    Beginning training model 3 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 3 of 20 finished in 00:00:00.0024151    Beginning training model 4 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 4 of 20 finished in 00:00:00.0053063    Beginning training model 5 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 5 of 20 finished in 00:00:00.0021594    Beginning training model 6 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 6 of 20 finished in 00:00:00.0026882    Beginning training model 7 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 7 of 20 finished in 00:00:00.0021936    Beginning training model 8 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 8 of 20 finished in 00:00:00.0021628    Beginning training model 9 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 13 instances with missing features during training (over 1 iterations; 13 inst/iter)    Trainer 9 of 20 finished in 00:00:00.0022445    Beginning training model 10 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 10 of 20 finished in 00:00:00.0021981    Beginning training model 11 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 17 instances with missing features during training (over 1 iterations; 17 inst/iter)    Trainer 11 of 20 finished in 00:00:00.0020985    Beginning training model 12 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 12 of 20 finished in 00:00:00.0021597    Beginning training model 13 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 13 of 20 finished in 00:00:00.0021872    Beginning training model 14 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 14 of 20 finished in 00:00:00.0021974    Beginning training model 15 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 19 instances with missing features during training (over 1 iterations; 19 inst/iter)    Trainer 15 of 20 finished in 00:00:00.0021324    Beginning training model 16 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 23 instances with missing features during training (over 1 iterations; 23 inst/iter)    Trainer 16 of 20 finished in 00:00:00.0021898    Beginning training model 17 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 17 of 20 finished in 00:00:00.0022213    Beginning training model 18 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 20 instances with missing features during training (over 1 iterations; 20 inst/iter)    Trainer 18 of 20 finished in 00:00:00.0022309    Beginning training model 19 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 13 instances with missing features during training (over 1 iterations; 13 inst/iter)    Trainer 19 of 20 finished in 00:00:00.0023464    Beginning training model 20 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 20 of 20 finished in 00:00:00.0022742    Warning:  10 of 20 trainings failed.    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 236 | 3 | 0.9874    negative || 14 | 430 | 0.9685    ||======================    Precision || 0.9440 | 0.9931 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.114893    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.876989    AUC: 0.996127      OVERALL RESULTS    ---------------------------------------    AUC: 0.996127 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.944000 (0.0000)    Positive recall: 0.987448 (0.0000)    Negative precision: 0.993072 (0.0000)    Negative recall: 0.968468 (0.0000)    Log-loss: 0.114893 (0.0000)    Log-loss reduction: 0.876989 (0.0000)    F1 Score: 0.965235 (0.0000)    AUPRC: 0.992160 (0.0000)      ---------------------------------------    Physical memory usage(MB): 184    Virtual memory usage(MB): 266794    09/21/2026 13:02:36 PM Time elapsed(s): 0.209      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Diverse-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Diverse-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Diverse-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Diverse-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 236 | 3 | 0.9874    negative || 14 | 430 | 0.9685    ||======================    Precision || 0.9440 | 0.9931 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.114893    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.876989    AUC: 0.996127      OVERALL RESULTS Starting test: Microsoft.ML.RunTests.TestPredictors.MulticlassLRNonNegativeTest    ---------------------------------------    AUC: 0.996127 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.944000 (0.0000)    Positive recall: 0.987448 (0.0000)    Negative precision: 0.993072 (0.0000)    Negative recall: 0.968468 (0.0000)    Log-loss: 0.114893 (0.0000)    Log-loss reduction: 0.876989 (0.0000)    F1 Score: 0.965235 (0.0000)    AUPRC: 0.992160 (0.0000)      ---------------------------------------    Physical memory usage(MB): 184    Virtual memory usage(MB): 266794    09/21/2026 13:02:36 PM Time elapsed(s): 0.078      Suffix of length 34 compared against sequence of length 119  Test EnsemblesBestDiverseSelectorTest: completed normally: passed  Test EnsemblesBestDiverseSelectorTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.DartLightGBMTest [SKIP]  LightGBM is 64-bit only  Microsoft.ML.RunTests.TestPredictors.RankingTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.MulticlassLRNonNegativeTest with memory usage 195,031,040.00 and max memory usage 195,031,040.00  Microsoft.ML.RunTests.TestPredictors.MulticlassLRNonNegativeTest [PASS] Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionGaussianNormTest  Output:  Running 'MulticlassLogisticRegression' on 'iris'  Running as: TrainTest tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1 nn=+} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt xf=Term{col=Label} out={/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris-model.zip} dout={/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris.txt} norm=no  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1 nn=+} norm=No dout=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris-model.zip seed=1 xf=Term{col=Label}    Not adding a normalizer.    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 48 | 2 | 0.9600    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9600 |0.9600 |    Accuracy(micro-avg): 0.973333    Accuracy(macro-avg): 0.973333    Log-loss: 0.099380    Log-loss reduction: 0.909540      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.973333 (0.0000)    Accuracy(macro-avg): 0.973333 (0.0000)    Log-loss: 0.099380 (0.0000)    Log-loss reduction: 0.909540 (0.0000)      ---------------------------------------    Physical memory usage(MB): 185    Virtual memory usage(MB): 266794    09/21/2026 13:02:37 PM Time elapsed(s): 0.112      Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/netcoreapp/LogisticRegression-Non-Negative-TrainTest-iris-out.txt  Output matches baseline: 'MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/netcoreapp/LogisticRegression-Non-Negative-TrainTest-iris-rp.txt  Output matches baseline: 'MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/netcoreapp/LogisticRegression-Non-Negative-TrainTest-iris.txt  Output matches baseline: 'MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-TrainTest-iris-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 48 | 2 | 0.9600    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9600 |0.9600 |    Accuracy(micro-avg): 0.973333    Accuracy(macro-avg): 0.973333    Log-loss: 0.099380    Log-loss reduction: 0.909540      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.973333 (0.0000)    Accuracy(macro-avg): 0.973333 (0.0000)    Log-loss: 0.099380 (0.0000)    Log-loss reduction: 0.909540 (0.0000)      ---------------------------------------    Physical memory usage(MB): 185    Virtual memory usage(MB): 266794    09/21/2026 13:02:37 PM Time elapsed(s): 0.13      Suffix of length 27 compared against sequence of length 34  Running 'MulticlassLogisticRegression' on 'iris'  Running as: CV tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1 nn=+} data=/root/helix/work/correlation/test/data/iris.txt seed=1 xf=Term{col=Label} dout={/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-CV-iris.txt} norm=no threads-  maml.exe CV tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1 nn=+} threads=- norm=No dout=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-CV-iris.txt data=/root/helix/work/correlation/test/data/iris.txt seed=1 xf=Term{col=Label}    Not adding a normalizer.    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 21 | 0 | 0 | 1.0000    1 || 0 | 29 | 1 | 0.9667    2 || 0 | 2 | 26 | 0.9286    ||========================    Precision ||1.0000 |0.9355 |0.9630 |    Accuracy(micro-avg): 0.962025    Accuracy(macro-avg): 0.965079    Log-loss: 0.129885    Log-loss reduction: 0.880567      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 29 | 0 | 0 | 1.0000    1 || 0 | 18 | 2 | 0.9000    2 || 0 | 0 | 22 | 1.0000    ||========================    Precision ||1.0000 |1.0000 |0.9167 |    Accuracy(micro-avg): 0.971831    Accuracy(macro-avg): 0.966667    Log-loss: 0.125565    Log-loss reduction: 0.884341      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.966928 (0.0049)    Accuracy(macro-avg): 0.965873 (0.0008)    Log-loss: 0.127725 (0.0022)    Log-loss reduction: 0.882454 (0.0019)      ---------------------------------------    Physical memory usage(MB): 185    Virtual memory usage(MB): 266794    09/21/2026 13:02:37 PM Time elapsed(s): 0.07      Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-CV-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/LogisticRegression-Non-Negative-CV-iris-out.txt  Output matches baseline: 'MulticlassLogisticRegression/LogisticRegression-Non-Negative-CV-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-CV-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/LogisticRegression-Non-Negative-CV-iris-rp.txt  Output matches baseline: 'MulticlassLogisticRegression/LogisticRegression-Non-Negative-CV-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/LogisticRegression-Non-Negative-CV-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/netcoreapp/LogisticRegression-Non-Negative-CV-iris.txt  Output matches baseline: 'MulticlassLogisticRegression/LogisticRegression-Non-Negative-CV-iris.txt'  Test MulticlassLRNonNegativeTest: completed normally: passed  Test MulticlassLRNonNegativeTest is using netcoreapp configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionGaussianNormTest with memory usage 195,244,032.00 and max memory usage 195,244,032.00 Starting test: Microsoft.ML.RunTests.TestPredictors.MulticlassTreeFeaturizedLRTest  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionGaussianNormTest [PASS]  Output:  Running 'LogisticRegression' on 'breast-cancer'  Running as: TrainTest tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer.txt} xf=MeanVarNormalizer{col=Features}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer-model.zip seed=1 xf=MeanVarNormalizer{col=Features}    Not adding a normalizer.    Warning:  Skipped 16 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 229 | 10 | 0.9582    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9582 | 0.9775 |    OVERALL 0/1 ACCURACY: 0.970717    LOG LOSS/instance: 0.110699    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.881479    AUC: 0.996231      OVERALL RESULTS    ---------------------------------------    AUC: 0.996231 (0.0000)    Accuracy: 0.970717 (0.0000)    Positive precision: 0.958159 (0.0000)    Positive recall: 0.958159 (0.0000)    Negative precision: 0.977477 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.110699 (0.0000)    Log-loss reduction: 0.881479 (0.0000)    F1 Score: 0.958159 (0.0000)    AUPRC: 0.992209 (0.0000)      ---------------------------------------    Physical memory usage(MB): 186    Virtual memory usage(MB): 266826    09/21/2026 13:02:37 PM Time elapsed(s): 0.052      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-GaussianNorm-TrainTest-breast-cancer-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-GaussianNorm-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-GaussianNorm-TrainTest-breast-cancer.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 229 | 10 | 0.9582    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9582 | 0.9775 |    OVERALL 0/1 ACCURACY: 0.970717    LOG LOSS/instance: 0.110699    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.881479    AUC: 0.996231      OVERALL RESULTS    ---------------------------------------    AUC: 0.996231 (0.0000)    Accuracy: 0.970717 (0.0000)    Positive precision: 0.958159 (0.0000)    Positive recall: 0.958159 (0.0000)    Negative precision: 0.977477 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.110699 (0.0000)    Log-loss reduction: 0.881479 (0.0000)    F1 Score: 0.958159 (0.0000)    AUPRC: 0.992209 (0.0000)      ---------------------------------------    Physical memory usage(MB): 186    Virtual memory usage(MB): 266826    09/21/2026 13:02:37 PM Time elapsed(s): 0.017      Suffix of length 34 compared against sequence of length 42  Running 'LogisticRegression' on 'breast-cancer'  Running as: CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-CV-breast-cancer.txt} xf=MeanVarNormalizer{col=Features} threads-  maml.exe CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} threads=- dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 xf=MeanVarNormalizer{col=Features}    Not adding a normalizer.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 9 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 129 | 5 | 0.9627    negative || 7 | 213 | 0.9682    ||======================    Precision || 0.9485 | 0.9771 |    OVERALL 0/1 ACCURACY: 0.966102    LOG LOSS/instance: 0.133256    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.860756    AUC: 0.994267    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 96 | 9 | 0.9143    negative || 3 | 221 | 0.9866    ||======================    Precision || 0.9697 | 0.9609 |    OVERALL 0/1 ACCURACY: 0.963526    LOG LOSS/instance: 0.117262    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.870207    AUC: 0.997449      OVERALL RESULTS    ---------------------------------------    AUC: 0.995858 (0.0016)    Accuracy: 0.964814 (0.0013)    Positive precision: 0.959113 (0.0106)    Positive recall: 0.938486 (0.0242)    Negative precision: 0.968967 (0.0081)    Negative recall: 0.977394 (0.0092)    Log-loss: 0.125259 (0.0080)    Log-loss reduction: 0.865481 (0.0047)    F1 Score: 0.948366 (0.0072)    AUPRC: 0.991982 (0.0025)      ---------------------------------------    Physical memory usage(MB): 186    Virtual memory usage(MB): 266826    09/21/2026 13:02:37 PM Time elapsed(s): 0.068      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-GaussianNorm-CV-breast-cancer-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-GaussianNorm-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-GaussianNorm-CV-breast-cancer-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-GaussianNorm-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-GaussianNorm-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-GaussianNorm-CV-breast-cancer.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-GaussianNorm-CV-breast-cancer.txt'  Test BinaryClassifierLogisticRegressionGaussianNormTest: completed normally: passed  Test BinaryClassifierLogisticRegressionGaussianNormTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.FastTreeUnderbuiltRegressionTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestIniModels.TestGamRegressionIni with memory usage 194,564,096.00 and max memory usage 195,211,264.00  Microsoft.ML.RunTests.TestIniModels.TestGamRegressionIni [PASS]  Output:  Test TestGamRegressionIni: aborted: passed Starting test: Microsoft.ML.RunTests.TestIniModels.TestGamBinaryClassificationIni Finished test: Microsoft.ML.RunTests.TestIniModels.TestGamBinaryClassificationIni with memory usage 193,261,568.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestIniModels.TestGamBinaryClassificationIni [PASS]  Output:  Test TestGamBinaryClassificationIni: aborted: passed  Microsoft.ML.RunTests.CmdLine.CmdParsingSingle [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.CmdLine.CmdParsingBasic [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestBaselines.AAACompareBaselines [SKIP]  Need CoreTLC specific baseline update Starting test: Microsoft.ML.RunTests.CmdLineReverseTests.NewTest Finished test: Microsoft.ML.RunTests.CmdLineReverseTests.NewTest with memory usage 193,306,624.00 and max memory usage 207,192,064.00 Starting test: Microsoft.ML.RunTests.CmdLineReverseTests.ArgumentParseTest Finished test: Microsoft.ML.RunTests.CmdLineReverseTests.ArgumentParseTest with memory usage 193,327,104.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.CmdIndenterTests.TestCmdIndenter [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestResultProcessor.RPProcessClassifierRegressorTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestResultProcessor.RPSingleClassifierTestWithSpace [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestResultProcessor.RPMulticlassifierTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestResultProcessor.RPSingleClassifierTestWIthEmptyLines [SKIP]  Need CoreTLC specific baseline update Starting test: Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths Finished test: Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths with memory usage 193,417,216.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths(directory: "absolute") [PASS]  Output:  Test ResultProcessorWithAbsolutePaths: completed normally: passed  Test ResultProcessorWithAbsolutePaths is using linux-arm64 configuration specific baselines. Starting test: Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths Finished test: Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths with memory usage 193,417,216.00 and max memory usage 207,192,064.00 Starting test: Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths  Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths(directory: "with spaces") [PASS]  Output:  Test ResultProcessorWithAbsolutePaths: completed normally: passed  Test ResultProcessorWithAbsolutePaths is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths with memory usage 193,417,216.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths(directory: "with {braces}") [PASS] Starting test: Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths  Output:  Test ResultProcessorWithAbsolutePaths: completed normally: passed  Test ResultProcessorWithAbsolutePaths is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths with memory usage 193,417,216.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestResultProcessor.ResultProcessorWithAbsolutePaths(directory: "with {unmatched brace") [PASS]  Output:  Test ResultProcessorWithAbsolutePaths: completed normally: passed  Test ResultProcessorWithAbsolutePaths is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestResultProcessor.RPSingleClassifierTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.MulticlassTreeFeaturizedLRTest with memory usage 193,351,680.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.MulticlassTreeFeaturizedLRTest [PASS]  Output:  Running 'MulticlassLogisticRegression' on 'iris-tree-featurized'  Running as: TrainTest tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt loader=Text{col=Label:U4[0-2]:0 col=Features:1-*} xf=TreeFeat{lps=0 trainer=ftr{iter=3}} xf=copy{col=Features:Leaves} out={/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-model.zip} dout={/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized.txt} norm=no  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1} norm=No dout=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized.txt loader=Text{col=Label:U4[0-2]:0 col=Features:1-*} data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-model.zip seed=1 xf=TreeFeat{lps=0 trainer=ftr{iter=3}} xf=copy{col=Features:Leaves}    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 150 instances    Binning and forming Feature objects    Reserved memory for tree learner: 20436 bytes    Starting to train ...    Not training a calibrator because it is not needed.    Not adding a normalizer.    Beginning optimization    num vars: 72    improvement criterion: Mean Improvement    L1 regularization selected 72 of 72 weights.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 49 | 1 | 0.9800    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9608 |0.9796 |    Accuracy(micro-avg): 0.980000    Accuracy(macro-avg): 0.980000    Log-loss: 0.048652    Log-loss reduction: 0.955715      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.980000 (0.0000)    Accuracy(macro-avg): 0.980000 (0.0000)    Log-loss: 0.048652 (0.0000)    Log-loss reduction: 0.955715 (0.0000)      ---------------------------------------    Physical memory usage(MB): 186    Virtual memory usage(MB): 266843    09/21/2026 13:02:38 PM Time elapsed(s): 0.285      Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-out.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-rp.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 49 | 1 | 0.9800    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9608 |0.9796 |    Accuracy(micro-avg): 0.980000    Accuracy(macro-avg): 0.980000    Log-loss: 0.048652    Log-loss reduction: 0.955715      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.980000 (0.0000)    Accuracy(macro-avg): 0.980000 (0.0000)    Log-loss: 0.048652 (0.0000)    Log-loss reduction: 0.955715 (0.0000) Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierFastRankClassificationTest      ---------------------------------------    Physical memory usage(MB): 186    Virtual memory usage(MB): 266843    09/21/2026 13:02:38 PM Time elapsed(s): 0.045      Suffix of length 27 compared against sequence of length 41  Running 'MulticlassLogisticRegression' on 'iris-tree-featurized'  Running as: CV tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/iris.txt seed=1 loader=Text{col=Label:U4[0-2]:0 col=Features:1-*} xf=TreeFeat{lps=0 trainer=ftr{iter=3}} xf=copy{col=Features:Leaves} dout={/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized.txt} norm=no threads-  maml.exe CV tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1} threads=- norm=No dout=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized.txt loader=Text{col=Label:U4[0-2]:0 col=Features:1-*} data=/root/helix/work/correlation/test/data/iris.txt seed=1 xf=TreeFeat{lps=0 trainer=ftr{iter=3}} xf=copy{col=Features:Leaves}    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 71 instances    Binning and forming Feature objects    Reserved memory for tree learner: 16380 bytes    Starting to train ...    Not training a calibrator because it is not needed.    Not adding a normalizer.    Beginning optimization    num vars: 39    improvement criterion: Mean Improvement    L1 regularization selected 39 of 39 weights.    Not training a calibrator because it is not needed.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 79 instances    Binning and forming Feature objects    Reserved memory for tree learner: 17472 bytes    Starting to train ...    Not training a calibrator because it is not needed.    Not adding a normalizer.    Beginning optimization    num vars: 54    improvement criterion: Mean Improvement    L1 regularization selected 54 of 54 weights.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 21 | 0 | 0 | 1.0000    1 || 0 | 25 | 5 | 0.8333    2 || 0 | 1 | 27 | 0.9643    ||========================    Precision ||1.0000 |0.9615 |0.8438 |    Accuracy(micro-avg): 0.924051    Accuracy(macro-avg): 0.932540    Log-loss: 0.330649    Log-loss reduction: 0.695959      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 29 | 0 | 0 | 1.0000    1 || 0 | 19 | 1 | 0.9500    2 || 0 | 2 | 20 | 0.9091    ||========================    Precision ||1.0000 |0.9048 |0.9524 |    Accuracy(micro-avg): 0.957746    Accuracy(macro-avg): 0.953030    Log-loss: 0.157832    Log-loss reduction: 0.854619      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.940899 (0.0168)    Accuracy(macro-avg): 0.942785 (0.0102)    Log-loss: 0.244241 (0.0864)    Log-loss reduction: 0.775289 (0.0793)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:39 PM Time elapsed(s): 1.666      Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-out.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-rp.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized.txt'  Running 'MulticlassLogisticRegression' on 'iris-tree-featurized-permuted'  Running as: TrainTest tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt loader=Text{col=Label:U4[0-2]:0 col=Features:1-*} xf=TreeFeat{lps=2 trainer=ftr{iter=3}} xf=copy{col=Features:Leaves} out={/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted-model.zip} dout={/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted.txt} norm=no  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1} norm=No dout=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted.txt loader=Text{col=Label:U4[0-2]:0 col=Features:1-*} data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted-model.zip seed=1 xf=TreeFeat{lps=2 trainer=ftr{iter=3}} xf=copy{col=Features:Leaves}    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 150 instances    Binning and forming Feature objects    Reserved memory for tree learner: 20436 bytes    Starting to train ...    Not training a calibrator because it is not needed.    Not adding a normalizer.    Beginning optimization    num vars: 81    improvement criterion: Mean Improvement    L1 regularization selected 81 of 81 weights.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 49 | 1 | 0.9800    2 || 0 | 3 | 47 | 0.9400    ||========================    Precision ||1.0000 |0.9423 |0.9792 |    Accuracy(micro-avg): 0.973333    Accuracy(macro-avg): 0.973333    Log-loss: 0.052580    Log-loss reduction: 0.952140      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.973333 (0.0000)    Accuracy(macro-avg): 0.973333 (0.0000)    Log-loss: 0.052580 (0.0000)    Log-loss reduction: 0.952140 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:39 PM Time elapsed(s): 0.036      Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted-out.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted-rp.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-TrainTest-iris-tree-featurized-permuted-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 49 | 1 | 0.9800    2 || 0 | 3 | 47 | 0.9400    ||========================    Precision ||1.0000 |0.9423 |0.9792 |    Accuracy(micro-avg): 0.973333    Accuracy(macro-avg): 0.973333    Log-loss: 0.052580    Log-loss reduction: 0.952140      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.973333 (0.0000)    Accuracy(macro-avg): 0.973333 (0.0000)    Log-loss: 0.052580 (0.0000)    Log-loss reduction: 0.952140 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:40 PM Time elapsed(s): 0.01      Suffix of length 27 compared against sequence of length 41  Running 'MulticlassLogisticRegression' on 'iris-tree-featurized-permuted'  Running as: CV tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/iris.txt seed=1 loader=Text{col=Label:U4[0-2]:0 col=Features:1-*} xf=TreeFeat{lps=2 trainer=ftr{iter=3}} xf=copy{col=Features:Leaves} dout={/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted.txt} norm=no threads-  maml.exe CV tr=MulticlassLogisticRegression{l1=0.001 l2=0.1 ot=1e-3 nt=1} threads=- norm=No dout=/root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted.txt loader=Text{col=Label:U4[0-2]:0 col=Features:1-*} data=/root/helix/work/correlation/test/data/iris.txt seed=1 xf=TreeFeat{lps=2 trainer=ftr{iter=3}} xf=copy{col=Features:Leaves}    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 71 instances    Binning and forming Feature objects    Reserved memory for tree learner: 16380 bytes    Starting to train ...    Not training a calibrator because it is not needed.    Not adding a normalizer.    Beginning optimization    num vars: 45    improvement criterion: Mean Improvement    L1 regularization selected 44 of 45 weights.    Not training a calibrator because it is not needed.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 79 instances    Binning and forming Feature objects    Reserved memory for tree learner: 17472 bytes    Starting to train ...    Not training a calibrator because it is not needed.    Not adding a normalizer.    Beginning optimization    num vars: 48    improvement criterion: Mean Improvement    L1 regularization selected 48 of 48 weights.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 21 | 0 | 0 | 1.0000    1 || 0 | 25 | 5 | 0.8333    2 || 0 | 1 | 27 | 0.9643    ||========================    Precision ||1.0000 |0.9615 |0.8438 |    Accuracy(micro-avg): 0.924051    Accuracy(macro-avg): 0.932540    Log-loss: 0.201590    Log-loss reduction: 0.814633      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 29 | 0 | 0 | 1.0000    1 || 0 | 19 | 1 | 0.9500    2 || 0 | 1 | 21 | 0.9545    ||========================    Precision ||1.0000 |0.9500 |0.9545 |    Accuracy(micro-avg): 0.971831    Accuracy(macro-avg): 0.968182    Log-loss: 0.101915    Log-loss reduction: 0.906125      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.947941 (0.0239)    Accuracy(macro-avg): 0.950361 (0.0178)    Log-loss: 0.151753 (0.0498)    Log-loss reduction: 0.860379 (0.0457)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:40 PM Time elapsed(s): 0.057      Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted-out.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted-rp.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted.txt  Output matches baseline: 'MulticlassLogisticRegression/MulticlassLogisticRegression-CV-iris-tree-featurized-permuted.txt'  Test MulticlassTreeFeaturizedLRTest: completed normally: passed  Microsoft.ML.RunTests.TestPredictors.GossLightGBMTest [SKIP]  LightGBM is 64-bit only Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierFastRankClassificationTest with memory usage 189,652,992.00 and max memory usage 207,192,064.00 Starting test: Microsoft.ML.RunTests.TestPredictors.TestTreeEnsembleCombinerWithCategoricalSplits  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierFastRankClassificationTest [PASS]  Output:  Running 'FastRank' on 'breast-cancer'  Running as: TrainTest tr=FastRank{nl=5 mil=5 lr=0.25 iter=20} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/FastRank/FastRank-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastRank/FastRank-TrainTest-breast-cancer.txt} eval=Binary{pr={/root/helix/work/workitem/e/TestOutput/FastRank/prcurve-breast-cancer-prcurve.txt }}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=FastRank{nl=5 mil=5 lr=0.25 iter=20} eval=Binary{pr={/root/helix/work/workitem/e/TestOutput/FastRank/prcurve-breast-cancer-prcurve.txt }} dout=/root/helix/work/workitem/e/TestOutput/FastRank/FastRank-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/FastRank/FastRank-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Processed 683 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Reserved memory for tree learner: 3852 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 240 | 1 | 0.9959    negative || 13 | 445 | 0.9716    ||======================    Precision || 0.9486 | 0.9978 |    OVERALL 0/1 ACCURACY: 0.979971    LOG LOSS/instance: 0.092572    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.900387    AUC: 0.995370      OVERALL RESULTS    ---------------------------------------    AUC: 0.995370 (0.0000)    Accuracy: 0.979971 (0.0000)    Positive precision: 0.948617 (0.0000)    Positive recall: 0.995851 (0.0000)    Negative precision: 0.997758 (0.0000)    Negative recall: 0.971616 (0.0000)    Log-loss: 0.092572 (0.0000)    Log-loss reduction: 0.900387 (0.0000)    F1 Score: 0.971660 (0.0000)    AUPRC: 0.970606 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:40 PM Time elapsed(s): 0.072      Comparing /root/helix/work/workitem/e/TestOutput/FastRank/FastRank-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastRank/FastRank-TrainTest-breast-cancer-out.txt  Output matches baseline: 'FastRank/FastRank-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastRank/FastRank-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastRank/FastRank-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'FastRank/FastRank-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastRank/FastRank-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastRank/FastRank-TrainTest-breast-cancer.txt  Output matches baseline: 'FastRank/FastRank-TrainTest-breast-cancer.txt'  maml.exe Test eval=Binary{pr={/root/helix/work/workitem/e/TestOutput/FastRank/prcurve-breast-cancer-prcurve.txt }} dout=/root/helix/work/workitem/e/TestOutput/FastRank/FastRank-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/FastRank/FastRank-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 240 | 1 | 0.9959    negative || 13 | 445 | 0.9716    ||======================    Precision || 0.9486 | 0.9978 |    OVERALL 0/1 ACCURACY: 0.979971    LOG LOSS/instance: 0.092572    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.900387    AUC: 0.995370      OVERALL RESULTS    ---------------------------------------    AUC: 0.995370 (0.0000)    Accuracy: 0.979971 (0.0000)    Positive precision: 0.948617 (0.0000)    Positive recall: 0.995851 (0.0000)    Negative precision: 0.997758 (0.0000)    Negative recall: 0.971616 (0.0000)    Log-loss: 0.092572 (0.0000)    Log-loss reduction: 0.900387 (0.0000)    F1 Score: 0.971660 (0.0000)    AUPRC: 0.970606 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:40 PM Time elapsed(s): 0.017      Suffix of length 33 compared against sequence of length 45  Running 'FastRank' on 'breast-cancer'  Running as: CV tr=FastRank{nl=5 mil=5 lr=0.25 iter=20} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/FastRank/FastRank-CV-breast-cancer.txt} threads-  maml.exe CV tr=FastRank{nl=5 mil=5 lr=0.25 iter=20} threads=- dout=/root/helix/work/workitem/e/TestOutput/FastRank/FastRank-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 8 instances with missing features during training    Processed 329 instances    Binning and forming Feature objects    Reserved memory for tree learner: 3852 bytes    Starting to train ...    Not training a calibrator because it is not needed.    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 8 instances with missing features during training    Processed 354 instances    Binning and forming Feature objects    Reserved memory for tree learner: 3816 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.3702 (134.0/(134.0+228.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 131 | 3 | 0.9776    negative || 10 | 218 | 0.9561    ||======================    Precision || 0.9291 | 0.9864 |    OVERALL 0/1 ACCURACY: 0.964088    LOG LOSS/instance: 0.211336    Test-set entropy (prior Log-Loss/instance): 0.950799    LOG-LOSS REDUCTION (RIG): 0.777728    AUC: 0.983225    TEST POSITIVE RATIO: 0.3175 (107.0/(107.0+230.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 98 | 9 | 0.9159    negative || 5 | 225 | 0.9783    ||======================    Precision || 0.9515 | 0.9615 |    OVERALL 0/1 ACCURACY: 0.958457    LOG LOSS/instance: 0.137700    Test-set entropy (prior Log-Loss/instance): 0.901650    LOG-LOSS REDUCTION (RIG): 0.847280    AUC: 0.993681      OVERALL RESULTS    ---------------------------------------    AUC: 0.988453 (0.0052)    Accuracy: 0.961273 (0.0028)    Positive precision: 0.940267 (0.0112)    Positive recall: 0.946750 (0.0309)    Negative precision: 0.973982 (0.0124)    Negative recall: 0.967201 (0.0111)    Log-loss: 0.174518 (0.0368)    Log-loss reduction: 0.812504 (0.0348)    F1 Score: 0.943030 (0.0097)    AUPRC: 0.962986 (0.0211)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:40 PM Time elapsed(s): 0.059      Comparing /root/helix/work/workitem/e/TestOutput/FastRank/FastRank-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastRank/FastRank-CV-breast-cancer-out.txt  Output matches baseline: 'FastRank/FastRank-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastRank/FastRank-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastRank/FastRank-CV-breast-cancer-rp.txt  Output matches baseline: 'FastRank/FastRank-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastRank/FastRank-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastRank/FastRank-CV-breast-cancer.txt  Output matches baseline: 'FastRank/FastRank-CV-breast-cancer.txt'  Test BinaryClassifierFastRankClassificationTest: completed normally: passed  Microsoft.ML.RunTests.TestPredictors.RegressorFastRankTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestPredictors.MulticlassifierLightGBMKeyLabelU404Test [SKIP]  LightGBM is 64-bit only  Microsoft.ML.RunTests.TestPredictors.RegressorOgdTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.TestTreeEnsembleCombinerWithCategoricalSplits with memory usage 162,639,872.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.TestTreeEnsembleCombinerWithCategoricalSplits [PASS]  Output:  Test TestTreeEnsembleCombinerWithCategoricalSplits: aborted: passed Starting test: Microsoft.ML.RunTests.TestPredictors.LinearClassifierTest Finished test: Microsoft.ML.RunTests.TestPredictors.LinearClassifierTest with memory usage 166,191,104.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.LinearClassifierTest [PASS]  Output:  Running 'SDCA' on 'breast-cancer'  Running as: TrainTest tr=SDCA{maxIterations=5 checkFreq=9 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=SDCA{maxIterations=5 checkFreq=9 nt=1} dout=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Using 1 thread to train.    Warning:  Skipped 16 instances with missing features/label during training    Auto-tuning parameters: L2 = 0.014641289.    Auto-tuning parameters: L1Threshold (L1/L2) = 0.    Using model from last iteration.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 222 | 17 | 0.9289    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9610 | 0.9624 |    OVERALL 0/1 ACCURACY: 0.961933    LOG LOSS/instance: 0.294964    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.684194    AUC: 0.995458      OVERALL RESULTS    ---------------------------------------    AUC: 0.995458 (0.0000)    Accuracy: 0.961933 (0.0000)    Positive precision: 0.961039 (0.0000)    Positive recall: 0.928870 (0.0000)    Negative precision: 0.962389 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.294964 (0.0000)    Log-loss reduction: 0.684194 (0.0000)    F1 Score: 0.944681 (0.0000)    AUPRC: 0.990716 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:40 PM Time elapsed(s): 0.029      Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-TrainTest-breast-cancer-out.txt  Output matches baseline: 'SDCA/BinarySDCA-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'SDCA/BinarySDCA-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-TrainTest-breast-cancer.txt  Output matches baseline: 'SDCA/BinarySDCA-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 222 | 17 | 0.9289    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9610 | 0.9624 |    OVERALL 0/1 ACCURACY: 0.961933    LOG LOSS/instance: 0.294964    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.684194    AUC: 0.995458      OVERALL RESULTS    ---------------------------------------    AUC: 0.995458 (0.0000)    Accuracy: 0.961933 (0.0000)    Positive precision: 0.961039 (0.0000)    Positive recall: 0.928870 (0.0000)    Negative precision: 0.962389 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.294964 (0.0000)    Log-loss reduction: 0.684194 (0.0000)    F1 Score: 0.944681 (0.0000)    AUPRC: 0.990716 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:40 PM Time elapsed(s): 0.076      Suffix of length 34 compared against sequence of length 42  Running 'SDCA' on 'breast-cancer'  Running as: CV tr=SDCA{maxIterations=5 checkFreq=9 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-CV-breast-cancer.txt} threads-  maml.exe CV tr=SDCA{maxIterations=5 checkFreq=9 nt=1} threads=- dout=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Using 1 thread to train.    Warning:  Skipped 8 instances with missing features/label during training    Auto-tuning parameters: L2 = 0.030395137.    Auto-tuning parameters: L1Threshold (L1/L2) = 0.    Using model from last iteration.    Not training a calibrator because it is not needed.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Using 1 thread to train.    Warning:  Skipped 8 instances with missing features/label during training    Auto-tuning parameters: L2 = 0.028248588.    Auto-tuning parameters: L1Threshold (L1/L2) = 0.    Using model from last iteration.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 125 | 9 | 0.9328    negative || 7 | 213 | 0.9682    ||======================    Precision || 0.9470 | 0.9595 |    OVERALL 0/1 ACCURACY: 0.954802    LOG LOSS/instance: 0.401674    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.580277    AUC: 0.993284    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 94 | 11 | 0.8952    negative || 2 | 222 | 0.9911    ||======================    Precision || 0.9792 | 0.9528 |    OVERALL 0/1 ACCURACY: 0.960486    LOG LOSS/instance: 0.390543    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.567722    AUC: 0.997321      OVERALL RESULTS    ---------------------------------------    AUC: 0.995303 (0.0020)    Accuracy: 0.957644 (0.0028)    Positive precision: 0.963068 (0.0161)    Positive recall: 0.914037 (0.0188)    Negative precision: 0.956125 (0.0033)    Negative recall: 0.979627 (0.0114)    Log-loss: 0.396109 (0.0056)    Log-loss reduction: 0.573999 (0.0063)    F1 Score: 0.937587 (0.0023)    AUPRC: 0.990827 (0.0033)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:40 PM Time elapsed(s): 0.022      Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-CV-breast-cancer-out.txt  Output matches baseline: 'SDCA/BinarySDCA-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-CV-breast-cancer-rp.txt  Output matches baseline: 'SDCA/BinarySDCA-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-CV-breast-cancer.txt  Output matches baseline: 'SDCA/BinarySDCA-CV-breast-cancer.txt'  Running 'SDCA' on 'breast-cancer'  Running as: TrainTest tr=SDCA{l2=1e-06 l1=0.5 maxIterations=5 checkFreq=9 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=SDCA{l2=1e-06 l1=0.5 maxIterations=5 checkFreq=9 nt=1} dout=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Using 1 thread to train.    Warning:  Skipped 16 instances with missing features/label during training    Using model from last iteration.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 220 | 19 | 0.9205    negative || 6 | 438 | 0.9865    ||======================    Precision || 0.9735 | 0.9584 |    OVERALL 0/1 ACCURACY: 0.963397    LOG LOSS/instance: 0.135137    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.855314    AUC: 0.996042      OVERALL RESULTS    ---------------------------------------    AUC: 0.996042 (0.0000)    Accuracy: 0.963397 (0.0000)    Positive precision: 0.973451 (0.0000)    Positive recall: 0.920502 (0.0000)    Negative precision: 0.958425 (0.0000)    Negative recall: 0.986486 (0.0000)    Log-loss: 0.135137 (0.0000)    Log-loss reduction: 0.855314 (0.0000)    F1 Score: 0.946237 (0.0000)    AUPRC: 0.991947 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:40 PM Time elapsed(s): 0.022      Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-L1-TrainTest-breast-cancer-out.txt  Output matches baseline: 'SDCA/BinarySDCA-L1-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-L1-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'SDCA/BinarySDCA-L1-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-L1-TrainTest-breast-cancer.txt  Output matches baseline: 'SDCA/BinarySDCA-L1-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 220 | 19 | 0.9205    negative || 6 | 438 | 0.9865    ||======================    Precision || 0.9735 | 0.9584 |    OVERALL 0/1 ACCURACY: 0.963397    LOG LOSS/instance: 0.135137    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.855314    AUC: 0.996042      OVERALL RESULTS    ---------------------------------------    AUC: 0.996042 (0.0000)    Accuracy: 0.963397 (0.0000)    Positive precision: 0.973451 (0.0000)    Positive recall: 0.920502 (0.0000)    Negative precision: 0.958425 (0.0000)    Negative recall: 0.986486 (0.0000)    Log-loss: 0.135137 (0.0000)    Log-loss reduction: 0.855314 (0.0000)    F1 Score: 0.946237 (0.0000)    AUPRC: 0.991947 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:41 PM Time elapsed(s): 0.01      Suffix of length 34 compared against sequence of length 40  Running 'SDCA' on 'breast-cancer'  Running as: CV tr=SDCA{l2=1e-06 l1=0.5 maxIterations=5 checkFreq=9 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-CV-breast-cancer.txt} threads-  maml.exe CV tr=SDCA{l2=1e-06 l1=0.5 maxIterations=5 checkFreq=9 nt=1} threads=- dout=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Using 1 thread to train.    Warning:  Skipped 8 instances with missing features/label during training  Starting test: Microsoft.ML.RunTests.TestPredictors.DefaultCalibratorPerceptronTest   Using model from last iteration.    Not training a calibrator because it is not needed.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Using 1 thread to train.    Warning:  Skipped 8 instances with missing features/label during training    Using model from last iteration.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 131 | 3 | 0.9776    negative || 8 | 212 | 0.9636    ||======================    Precision || 0.9424 | 0.9860 |    OVERALL 0/1 ACCURACY: 0.968927    LOG LOSS/instance: 0.142232    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.851377    AUC: 0.993860    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 96 | 9 | 0.9143    negative || 2 | 222 | 0.9911    ||======================    Precision || 0.9796 | 0.9610 |    OVERALL 0/1 ACCURACY: 0.966565    LOG LOSS/instance: 0.118621    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.868703    AUC: 0.997449      OVERALL RESULTS    ---------------------------------------    AUC: 0.995655 (0.0018)    Accuracy: 0.967746 (0.0012)    Positive precision: 0.961019 (0.0186)    Positive recall: 0.945949 (0.0317)    Negative precision: 0.973543 (0.0125)    Negative recall: 0.977354 (0.0137)    Log-loss: 0.130426 (0.0118)    Log-loss reduction: 0.860040 (0.0087)    F1 Score: 0.952760 (0.0069)    AUPRC: 0.991454 (0.0030)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:41 PM Time elapsed(s): 0.03      Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-L1-CV-breast-cancer-out.txt  Output matches baseline: 'SDCA/BinarySDCA-L1-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-L1-CV-breast-cancer-rp.txt  Output matches baseline: 'SDCA/BinarySDCA-L1-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-L1-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-L1-CV-breast-cancer.txt  Output matches baseline: 'SDCA/BinarySDCA-L1-CV-breast-cancer.txt'  Running 'SDCA' on 'breast-cancer'  Running as: TrainTest tr=SDCA{l2=1e-06 loss=SmoothedHinge l1=0.5 maxIterations=5 checkFreq=9 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=SDCA{l2=1e-06 loss=SmoothedHinge l1=0.5 maxIterations=5 checkFreq=9 nt=1} dout=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Using 1 thread to train.    Warning:  Skipped 16 instances with missing features/label during training    Using model from last iteration.    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 224 | 15 | 0.9372    negative || 8 | 436 | 0.9820    ||======================    Precision || 0.9655 | 0.9667 |    OVERALL 0/1 ACCURACY: 0.966325    LOG LOSS/instance: 0.118542    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.873081    AUC: 0.995816      OVERALL RESULTS    ---------------------------------------    AUC: 0.995816 (0.0000)    Accuracy: 0.966325 (0.0000)    Positive precision: 0.965517 (0.0000)    Positive recall: 0.937238 (0.0000)    Negative precision: 0.966741 (0.0000)    Negative recall: 0.981982 (0.0000)    Log-loss: 0.118542 (0.0000)    Log-loss reduction: 0.873081 (0.0000)    F1 Score: 0.951168 (0.0000)    AUPRC: 0.991045 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:41 PM Time elapsed(s): 0.02      Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer-out.txt  Output matches baseline: 'SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer.txt  Output matches baseline: 'SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 224 | 15 | 0.9372    negative || 8 | 436 | 0.9820    ||======================    Precision || 0.9655 | 0.9667 |    OVERALL 0/1 ACCURACY: 0.966325    LOG LOSS/instance: 0.118542    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.873081    AUC: 0.995816      OVERALL RESULTS    ---------------------------------------    AUC: 0.995816 (0.0000)    Accuracy: 0.966325 (0.0000)    Positive precision: 0.965517 (0.0000)    Positive recall: 0.937238 (0.0000)    Negative precision: 0.966741 (0.0000)    Negative recall: 0.981982 (0.0000)    Log-loss: 0.118542 (0.0000)    Log-loss reduction: 0.873081 (0.0000)    F1 Score: 0.951168 (0.0000)    AUPRC: 0.991045 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:41 PM Time elapsed(s): 0.007      Suffix of length 34 compared against sequence of length 40  Running 'SDCA' on 'breast-cancer'  Running as: CV tr=SDCA{l2=1e-06 loss=SmoothedHinge l1=0.5 maxIterations=5 checkFreq=9 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer.txt} threads-  maml.exe CV tr=SDCA{l2=1e-06 loss=SmoothedHinge l1=0.5 maxIterations=5 checkFreq=9 nt=1} threads=- dout=/root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Using 1 thread to train.    Warning:  Skipped 8 instances with missing features/label during training    Using model from last iteration.    Training calibrator.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Using 1 thread to train.    Warning:  Skipped 8 instances with missing features/label during training    Using model from last iteration.    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 130 | 4 | 0.9701    negative || 8 | 212 | 0.9636    ||======================    Precision || 0.9420 | 0.9815 |    OVERALL 0/1 ACCURACY: 0.966102    LOG LOSS/instance: 0.129889    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.864274    AUC: 0.994539    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 38 | 67 | 0.3619    negative || 0 | 224 | 1.0000    ||======================    Precision || 1.0000 | 0.7698 |    OVERALL 0/1 ACCURACY: 0.796353    LOG LOSS/instance: 0.126797    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.859653    AUC: 0.996854      OVERALL RESULTS    ---------------------------------------    AUC: 0.995696 (0.0012)    Accuracy: 0.881227 (0.0849)    Positive precision: 0.971014 (0.0290)    Positive recall: 0.666027 (0.3041)    Negative precision: 0.875620 (0.1059)    Negative recall: 0.981818 (0.0182)    Log-loss: 0.128343 (0.0015)    Log-loss reduction: 0.861964 (0.0023)    F1 Score: 0.743675 (0.2122)    AUPRC: 0.991479 (0.0016)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:41 PM Time elapsed(s): 0.031      Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer-out.txt  Output matches baseline: 'SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer-rp.txt  Output matches baseline: 'SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer.txt  Output matches baseline: 'SDCA/BinarySDCA-SmoothedHinge-CV-breast-cancer.txt'  Running 'SGD' on 'breast-cancer'  Running as: TrainTest tr=SGD{maxIterations=2 checkFreq=9 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=SGD{maxIterations=2 checkFreq=9 nt=1} dout=/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 16 instances with missing features during training    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 225 | 14 | 0.9414    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9615 | 0.9688 |    OVERALL 0/1 ACCURACY: 0.966325    LOG LOSS/instance: 0.494040    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.471051    AUC: 0.995156      OVERALL RESULTS    ---------------------------------------    AUC: 0.995156 (0.0000)    Accuracy: 0.966325 (0.0000)    Positive precision: 0.961538 (0.0000)    Positive recall: 0.941423 (0.0000)    Negative precision: 0.968820 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.494040 (0.0000)    Log-loss reduction: 0.471051 (0.0000)    F1 Score: 0.951374 (0.0000)    AUPRC: 0.990094 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:41 PM Time elapsed(s): 0.018      Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-TrainTest-breast-cancer-out.txt  Output matches baseline: 'SGD/BinarySGD-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'SGD/BinarySGD-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-TrainTest-breast-cancer.txt  Output matches baseline: 'SGD/BinarySGD-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 225 | 14 | 0.9414    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9615 | 0.9688 |    OVERALL 0/1 ACCURACY: 0.966325    LOG LOSS/instance: 0.494040    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.471051    AUC: 0.995156      OVERALL RESULTS    ---------------------------------------    AUC: 0.995156 (0.0000)    Accuracy: 0.966325 (0.0000)    Positive precision: 0.961538 (0.0000)    Positive recall: 0.941423 (0.0000)    Negative precision: 0.968820 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.494040 (0.0000)    Log-loss reduction: 0.471051 (0.0000)    F1 Score: 0.951374 (0.0000)    AUPRC: 0.990094 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:41 PM Time elapsed(s): 0.009      Suffix of length 34 compared against sequence of length 38  Running 'SGD' on 'breast-cancer'  Running as: CV tr=SGD{maxIterations=2 checkFreq=9 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-CV-breast-cancer.txt} threads-  maml.exe CV tr=SGD{maxIterations=2 checkFreq=9 nt=1} threads=- dout=/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 8 instances with missing features during training    Not training a calibrator because it is not needed.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 8 instances with missing features during training    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 124 | 10 | 0.9254    negative || 6 | 214 | 0.9727    ||======================    Precision || 0.9538 | 0.9554 |    OVERALL 0/1 ACCURACY: 0.954802    LOG LOSS/instance: 0.670855    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.299001    AUC: 0.993046    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 97 | 8 | 0.9238    negative || 2 | 222 | 0.9911    ||======================    Precision || 0.9798 | 0.9652 |    OVERALL 0/1 ACCURACY: 0.969605    LOG LOSS/instance: 0.657158    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.272615    AUC: 0.997066      OVERALL RESULTS    ---------------------------------------    AUC: 0.995056 (0.0020)    Accuracy: 0.962204 (0.0074)    Positive precision: 0.966822 (0.0130)    Positive recall: 0.924591 (0.0008)    Negative precision: 0.960287 (0.0049)    Negative recall: 0.981899 (0.0092)    Log-loss: 0.664007 (0.0068)    Log-loss reduction: 0.285808 (0.0132)    F1 Score: 0.945187 (0.0058)    AUPRC: 0.990233 (0.0032)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:41 PM Time elapsed(s): 0.021      Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-CV-breast-cancer-out.txt  Output matches baseline: 'SGD/BinarySGD-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-CV-breast-cancer-rp.txt  Output matches baseline: 'SGD/BinarySGD-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-CV-breast-cancer.txt  Output matches baseline: 'SGD/BinarySGD-CV-breast-cancer.txt'  Running 'SGD' on 'breast-cancer'  Running as: TrainTest tr=SGD{loss=Hinge maxIterations=2 checkFreq=9 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=SGD{loss=Hinge maxIterations=2 checkFreq=9 nt=1} dout=/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 16 instances with missing features during training    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 228 | 11 | 0.9540    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9580 | 0.9753 |    OVERALL 0/1 ACCURACY: 0.969253    LOG LOSS/instance: 0.129716    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.861119    AUC: 0.995307      OVERALL RESULTS    ---------------------------------------    AUC: 0.995307 (0.0000)    Accuracy: 0.969253 (0.0000)    Positive precision: 0.957983 (0.0000)    Positive recall: 0.953975 (0.0000)    Negative precision: 0.975281 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.129716 (0.0000)    Log-loss reduction: 0.861119 (0.0000)    F1 Score: 0.955975 (0.0000)    AUPRC: 0.990403 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:42 PM Time elapsed(s): 0.02      Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-Hinge-TrainTest-breast-cancer-out.txt  Output matches baseline: 'SGD/BinarySGD-Hinge-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-Hinge-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'SGD/BinarySGD-Hinge-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-Hinge-TrainTest-breast-cancer.txt  Output matches baseline: 'SGD/BinarySGD-Hinge-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 228 | 11 | 0.9540    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9580 | 0.9753 |    OVERALL 0/1 ACCURACY: 0.969253    LOG LOSS/instance: 0.129716    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.861119    AUC: 0.995307      OVERALL RESULTS    ---------------------------------------    AUC: 0.995307 (0.0000)    Accuracy: 0.969253 (0.0000)    Positive precision: 0.957983 (0.0000)    Positive recall: 0.953975 (0.0000)    Negative precision: 0.975281 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.129716 (0.0000)    Log-loss reduction: 0.861119 (0.0000)    F1 Score: 0.955975 (0.0000)    AUPRC: 0.990403 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:42 PM Time elapsed(s): 0.007      Suffix of length 34 compared against sequence of length 38  Running 'SGD' on 'breast-cancer'  Running as: CV tr=SGD{loss=Hinge maxIterations=2 checkFreq=9 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-CV-breast-cancer.txt} threads-  maml.exe CV tr=SGD{loss=Hinge maxIterations=2 checkFreq=9 nt=1} threads=- dout=/root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 8 instances with missing features during training    Training calibrator.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 8 instances with missing features during training    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 125 | 9 | 0.9328    negative || 7 | 213 | 0.9682    ||======================    Precision || 0.9470 | 0.9595 |    OVERALL 0/1 ACCURACY: 0.954802    LOG LOSS/instance: 0.150656    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.842575    AUC: 0.993114    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 94 | 11 | 0.8952    negative || 2 | 222 | 0.9911    ||======================    Precision || 0.9792 | 0.9528 |    OVERALL 0/1 ACCURACY: 0.960486    LOG LOSS/instance: 0.127422    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.858961    AUC: 0.997109      OVERALL RESULTS    ---------------------------------------    AUC: 0.995111 (0.0020)    Accuracy: 0.957644 (0.0028)    Positive precision: 0.963068 (0.0161)    Positive recall: 0.914037 (0.0188)    Negative precision: 0.956125 (0.0033)    Negative recall: 0.979627 (0.0114)    Log-loss: 0.139039 (0.0116)    Log-loss reduction: 0.850768 (0.0082)    F1 Score: 0.937587 (0.0023)    AUPRC: 0.990374 (0.0032)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:42 PM Time elapsed(s): 0.014      Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-Hinge-CV-breast-cancer-out.txt  Output matches baseline: 'SGD/BinarySGD-Hinge-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-Hinge-CV-breast-cancer-rp.txt  Output matches baseline: 'SGD/BinarySGD-Hinge-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/SGD/BinarySGD-Hinge-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/SGD/BinarySGD-Hinge-CV-breast-cancer.txt  Output matches baseline: 'SGD/BinarySGD-Hinge-CV-breast-cancer.txt'  Test LinearClassifierTest: completed normally: passed  Microsoft.ML.RunTests.TestPredictors.RankingLightGBMTest [SKIP]  Need to find ranking dataset.  Microsoft.ML.RunTests.TestPredictors.GamRegressionTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestPredictors.OneClassSvmLibsvmWrapperDenseTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestPredictors.RegressorLightGBMRMSETest [SKIP]  LightGBM is 64-bit only Finished test: Microsoft.ML.RunTests.TestPredictors.DefaultCalibratorPerceptronTest with memory usage 166,281,216.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.DefaultCalibratorPerceptronTest [FAIL]  Assert.Equal() Failure: Values differ  Expected: 0  Actual: 2  Stack Trace:  /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs(221,0): at Microsoft.ML.RunTests.BaseTestBaseline.Done()  /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs(1615,0): at Microsoft.ML.RunTests.TestPredictors.DefaultCalibratorPerceptronTest()  at System.RuntimeMethodHandle.InvokeMethod(Object target, Void** arguments, Signature sig, Boolean isConstructor)  at System.Reflection.MethodBaseInvoker.InvokeWithNoArgs(Object obj, BindingFlags invokeAttr)  Output: Starting test: Microsoft.ML.RunTests.TestPredictors.FastForestRegressionTest  Running 'AveragedPerceptron' on 'breast-cancer'  Running as: TrainTest tr=AveragedPerceptron data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration-model.zip} dout={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration.txt} cali={}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=AveragedPerceptron cali={} dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 160 instances with missing features during training (over 10 iterations; 16 inst/iter)    Not training a calibrator because a valid calibrator trainer was not provided.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 234 | 5 | 0.9791    negative || 12 | 432 | 0.9730    ||======================    Precision || 0.9512 | 0.9886 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: NaN    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.000000    AUC: 0.996146      OVERALL RESULTS    ---------------------------------------    AUC: 0.996146 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.951220 (0.0000)    Positive recall: 0.979079 (0.0000)    Negative precision: 0.988558 (0.0000)    Negative recall: 0.972973 (0.0000)    Log-loss: NaN (0.0000)    Log-loss reduction: 0.000000 (0.0000)    F1 Score: 0.964948 (0.0000)    AUPRC: 0.992065 (0.0000)      ---------------------------------------    Warning:  Data does not contain a probability column. Will not output the Log-loss column    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:42 PM Time elapsed(s): 0.013      Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer.nocalibration-out.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer.nocalibration-rp.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer.nocalibration.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.nocalibration-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 234 | 5 | 0.9791    negative || 12 | 432 | 0.9730    ||======================    Precision || 0.9512 | 0.9886 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: NaN    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.000000    AUC: 0.996146      OVERALL RESULTS    ---------------------------------------    AUC: 0.996146 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.951220 (0.0000)    Positive recall: 0.979079 (0.0000)    Negative precision: 0.988558 (0.0000)    Negative recall: 0.972973 (0.0000)    Log-loss: NaN (0.0000)    Log-loss reduction: 0.000000 (0.0000)    F1 Score: 0.964948 (0.0000)    AUPRC: 0.992065 (0.0000)      ---------------------------------------    Warning:  Data does not contain a probability column. Will not output the Log-loss column    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:42 PM Time elapsed(s): 0.014      Suffix of length 35 compared against sequence of length 39  Running 'AveragedPerceptron' on 'breast-cancer'  Running as: CV tr=AveragedPerceptron data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.nocalibration.txt} threads- cali={}  maml.exe CV tr=AveragedPerceptron threads=- cali={} dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.nocalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 80 instances with missing features during training (over 10 iterations; 8 inst/iter)    Not training a calibrator because a valid calibrator trainer was not provided.    Warning:  Data does not contain a probability column. Will not output the Log-loss column    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 80 instances with missing features during training (over 10 iterations; 8 inst/iter)    Not training a calibrator because a valid calibrator trainer was not provided.    Warning:  Data does not contain a probability column. Will not output the Log-loss column    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 133 | 1 | 0.9925    negative || 9 | 211 | 0.9591    ||======================    Precision || 0.9366 | 0.9953 |    OVERALL 0/1 ACCURACY: 0.971751    LOG LOSS/instance: NaN    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.000000    AUC: 0.994403    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 100 | 5 | 0.9524    negative || 3 | 221 | 0.9866    ||======================    Precision || 0.9709 | 0.9779 |    OVERALL 0/1 ACCURACY: 0.975684    LOG LOSS/instance: NaN    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.000000    AUC: 0.997619      OVERALL RESULTS    ---------------------------------------    AUC: 0.996011 (0.0016)    Accuracy: 0.973718 (0.0020)    Positive precision: 0.953747 (0.0171)    Positive recall: 0.972459 (0.0201)    Negative precision: 0.986580 (0.0087)    Negative recall: 0.972849 (0.0138)    Log-loss: NaN (NaN)    Log-loss reduction: 0.000000 (0.0000)    F1 Score: 0.962653 (0.0011)    AUPRC: 0.992269 (0.0025)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:42 PM Time elapsed(s): 0.012      Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.nocalibration-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer.nocalibration-out.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.nocalibration-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.nocalibration-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer.nocalibration-rp.txt  *** Failure #1: Values to compare are 0.996028 and 0.996011  AllowedVariance: 1E-05  delta: 2E-05  delta2: 2E-05   Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean MatchNumberWithTolerance(System.Text.RegularExpressions.MatchCollection, System.Text.RegularExpressions.MatchCollection, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 615  Boolean GetNumbersFromFile(System.String ByRef, System.String ByRef, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 581  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 556  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_CV(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 445  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 366  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void DefaultCalibratorPerceptronTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 1614  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  *** Failure #2: Output and baseline mismatch at line 3, expected '0.996028 0.972305 0.95666 0.964996 0.981961 0.975122 NaN 0 0.960623 0.99228 AveragedPerceptron %Data% %Output% 99 0 0 maml.exe CV tr=AveragedPerceptron threads=- cali={} dout=%Output% data=%Data% seed=1 ' but got '0.996011 0.973718 0.953747 0.972459 0.98658 0.972849 NaN 0 0.962653 0.992269 AveragedPerceptron %Data% %Output% 99 0 0 maml.exe CV tr=AveragedPerceptron threads=- cali={} dout=%Output% data=%Data% seed=1 ' : 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.nocalibration-rp.txt'  Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 566  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_CV(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 445  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 366  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void DefaultCalibratorPerceptronTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 1614  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.nocalibration.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer.nocalibration.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.nocalibration.txt'  Test DefaultCalibratorPerceptronTest: completed normally: failed  Test DefaultCalibratorPerceptronTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.PoissonRegressorTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestPredictors.EarlyStoppingTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestPredictors.PcaAnomalyTest [SKIP]  Test flaky. Disabling until resolved.  Microsoft.ML.RunTests.TestPredictors.WeightingRankingPredictorsTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.FastForestRegressionTest with memory usage 170,811,392.00 and max memory usage 207,192,064.00 Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierTesterThresholdingTest  Microsoft.ML.RunTests.TestPredictors.FastForestRegressionTest [PASS]  Output:  Running 'FastForestRegression' on 'housing'  Running as: TrainTest tr=FastForestRegression{nl=5 mil=5 iter=20} data=/root/helix/work/correlation/test/data/housing.txt seed=1 test=/root/helix/work/correlation/test/data/housing.txt loader=Text{col=Label:0 col=Features:~ header=+} out={/root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-TrainTest-housing-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-TrainTest-housing.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/housing.txt tr=FastForestRegression{nl=5 mil=5 iter=20} dout=/root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-TrainTest-housing.txt loader=Text{col=Label:0 col=Features:~ header=+} data=/root/helix/work/correlation/test/data/housing.txt out=/root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-TrainTest-housing-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 506 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Reserved memory for tree learner: 67032 bytes    Starting to train ...    Not training a calibrator because it is not needed.    L1(avg): 2.970635    L2(avg): 17.744904    RMS(avg): 4.212470    Loss-fn(avg): 17.744904    R Squared: 0.789801      OVERALL RESULTS    ---------------------------------------    L1(avg): 2.970635 (0.0000)    L2(avg): 17.744904 (0.0000)    RMS(avg): 4.212470 (0.0000)    Loss-fn(avg): 17.744904 (0.0000)    R Squared: 0.789801 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:42 PM Time elapsed(s): 0.096      Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-TrainTest-housing-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/FastForestRegression-TrainTest-housing-out.txt  Output matches baseline: 'FastForestRegression/FastForestRegression-TrainTest-housing-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-TrainTest-housing-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/FastForestRegression-TrainTest-housing-rp.txt  Output matches baseline: 'FastForestRegression/FastForestRegression-TrainTest-housing-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-TrainTest-housing.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/FastForestRegression-TrainTest-housing.txt  Output matches baseline: 'FastForestRegression/FastForestRegression-TrainTest-housing.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-TrainTest-housing.txt data=/root/helix/work/correlation/test/data/housing.txt in=/root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-TrainTest-housing-model.zip seed=1    L1(avg): 2.970635    L2(avg): 17.744904    RMS(avg): 4.212470    Loss-fn(avg): 17.744904    R Squared: 0.789801      OVERALL RESULTS    ---------------------------------------    L1(avg): 2.970635 (0.0000)    L2(avg): 17.744904 (0.0000)    RMS(avg): 4.212470 (0.0000)    Loss-fn(avg): 17.744904 (0.0000)    R Squared: 0.789801 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:42 PM Time elapsed(s): 0.01      Suffix of length 19 compared against sequence of length 29  Running 'FastForestRegression' on 'housing'  Running as: CV tr=FastForestRegression{nl=5 mil=5 iter=20} data=/root/helix/work/correlation/test/data/housing.txt seed=1 loader=Text{col=Label:0 col=Features:~ header=+} dout={/root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-CV-housing.txt} threads-  maml.exe CV tr=FastForestRegression{nl=5 mil=5 iter=20} threads=- dout=/root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-CV-housing.txt loader=Text{col=Label:0 col=Features:~ header=+} data=/root/helix/work/correlation/test/data/housing.txt seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 241 instances    Binning and forming Feature objects    Reserved memory for tree learner: 56772 bytes    Starting to train ...    Not training a calibrator because it is not needed.    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 265 instances    Binning and forming Feature objects    Reserved memory for tree learner: 60444 bytes    Starting to train ...    Not training a calibrator because it is not needed.    L1(avg): 3.297530    L2(avg): 22.053650    RMS(avg): 4.696131    Loss-fn(avg): 22.053650    R Squared: 0.736495    L1(avg): 3.262365    L2(avg): 19.891088    RMS(avg): 4.459943    Loss-fn(avg): 19.891088    R Squared: 0.766574      OVERALL RESULTS    ---------------------------------------    L1(avg): 3.279948 (0.0176)    L2(avg): 20.972369 (1.0813)    RMS(avg): 4.578037 (0.1181)    Loss-fn(avg): 20.972369 (1.0813)    R Squared: 0.751534 (0.0150)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:42 PM Time elapsed(s): 0.09      Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-CV-housing-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/FastForestRegression-CV-housing-out.txt  Output matches baseline: 'FastForestRegression/FastForestRegression-CV-housing-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-CV-housing-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/FastForestRegression-CV-housing-rp.txt  Output matches baseline: 'FastForestRegression/FastForestRegression-CV-housing-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/FastForestRegression-CV-housing.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/FastForestRegression-CV-housing.txt  Output matches baseline: 'FastForestRegression/FastForestRegression-CV-housing.txt'  Running 'FastForestRegression' on 'housing'  Running as: TrainTest tr=FastForestRegression{nl=5 mil=5 iter=20} data=/root/helix/work/correlation/test/data/housing.txt seed=1 test=/root/helix/work/correlation/test/data/housing.txt loader=Text{col=Label:0 col=Features:~ header=+} out={/root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-TrainTest-housing-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-TrainTest-housing.txt} scorer=QuantileRegression{quantiles = 0.25,0.5,0.75}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/housing.txt tr=FastForestRegression{nl=5 mil=5 iter=20} scorer=QuantileRegression{quantiles = 0.25,0.5,0.75} dout=/root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-TrainTest-housing.txt loader=Text{col=Label:0 col=Features:~ header=+} data=/root/helix/work/correlation/test/data/housing.txt out=/root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-TrainTest-housing-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 506 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Reserved memory for tree learner: 67032 bytes    Starting to train ...    Not training a calibrator because it is not needed.    L1(avg): 2.840810    L2(avg): 17.723068    RMS(avg): 4.209877    Loss-fn(avg): 17.723068    R Squared: 0.790060      OVERALL RESULTS    ---------------------------------------    L1(avg): 2.840810 (0.0000)    L2(avg): 17.723068 (0.0000)    RMS(avg): 4.209877 (0.0000)    Loss-fn(avg): 17.723068 (0.0000)    R Squared: 0.790060 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:43 PM Time elapsed(s): 0.34      Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-TrainTest-housing-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/QuantileRegressorTester-TrainTest-housing-out.txt  Output matches baseline: 'FastForestRegression/QuantileRegressorTester-TrainTest-housing-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-TrainTest-housing-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/QuantileRegressorTester-TrainTest-housing-rp.txt  Output matches baseline: 'FastForestRegression/QuantileRegressorTester-TrainTest-housing-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-TrainTest-housing.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/QuantileRegressorTester-TrainTest-housing.txt  Output matches baseline: 'FastForestRegression/QuantileRegressorTester-TrainTest-housing.txt'  maml.exe Test scorer=QuantileRegression{quantiles = 0.25,0.5,0.75} dout=/root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-TrainTest-housing.txt data=/root/helix/work/correlation/test/data/housing.txt in=/root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-TrainTest-housing-model.zip seed=1    L1(avg): 2.840810    L2(avg): 17.723068    RMS(avg): 4.209877    Loss-fn(avg): 17.723068    R Squared: 0.790060      OVERALL RESULTS    ---------------------------------------    L1(avg): 2.840810 (0.0000)    L2(avg): 17.723068 (0.0000)    RMS(avg): 4.209877 (0.0000)    Loss-fn(avg): 17.723068 (0.0000)    R Squared: 0.790060 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:43 PM Time elapsed(s): 0.364      Suffix of length 19 compared against sequence of length 29  Running 'FastForestRegression' on 'housing'  Running as: CV tr=FastForestRegression{nl=5 mil=5 iter=20} data=/root/helix/work/correlation/test/data/housing.txt seed=1 loader=Text{col=Label:0 col=Features:~ header=+} dout={/root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-CV-housing.txt} threads- scorer=QuantileRegression{quantiles = 0.25,0.5,0.75}  maml.exe CV tr=FastForestRegression{nl=5 mil=5 iter=20} scorer=QuantileRegression{quantiles = 0.25,0.5,0.75} threads=- dout=/root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-CV-housing.txt loader=Text{col=Label:0 col=Features:~ header=+} data=/root/helix/work/correlation/test/data/housing.txt seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 241 instances    Binning and forming Feature objects    Reserved memory for tree learner: 56772 bytes    Starting to train ...    Not training a calibrator because it is not needed.    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 265 instances    Binning and forming Feature objects    Reserved memory for tree learner: 60444 bytes    Starting to train ...    Not training a calibrator because it is not needed.    L1(avg): 3.180943    L2(avg): 22.529859    RMS(avg): 4.746563    Loss-fn(avg): 22.529858    R Squared: 0.730805    L1(avg): 3.240456    L2(avg): 20.642272    RMS(avg): 4.543377    Loss-fn(avg): 20.642272    R Squared: 0.757759      OVERALL RESULTS    ---------------------------------------    L1(avg): 3.210700 (0.0298)    L2(avg): 21.586065 (0.9438)    RMS(avg): 4.644970 (0.1016)    Loss-fn(avg): 21.586065 (0.9438)    R Squared: 0.744282 (0.0135)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:43 PM Time elapsed(s): 0.302      Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-CV-housing-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/QuantileRegressorTester-CV-housing-out.txt  Output matches baseline: 'FastForestRegression/QuantileRegressorTester-CV-housing-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-CV-housing-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/QuantileRegressorTester-CV-housing-rp.txt  Output matches baseline: 'FastForestRegression/QuantileRegressorTester-CV-housing-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestRegression/QuantileRegressorTester-CV-housing.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestRegression/QuantileRegressorTester-CV-housing.txt  Output matches baseline: 'FastForestRegression/QuantileRegressorTester-CV-housing.txt'  Test FastForestRegressionTest: completed normally: passed  Microsoft.ML.RunTests.TestPredictors.WeightingClassificationLRPredictorsTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierTesterThresholdingTest with memory usage 170,815,488.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierTesterThresholdingTest [PASS]  Output:  Running 'LogisticRegression' on 'breast-cancer'  Running as: TrainTest tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold-model.zip} dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold.txt} norm=no eval=BinaryClassifier{threshold=0.95 useRawScore=-}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} eval=BinaryClassifier{threshold=0.95 useRawScore=-} norm=No dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold-model.zip seed=1    Not adding a normalizer.    Warning:  Skipped 16 instances with missing features/label/weight during training  Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiAveragerTest   Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 198 | 41 | 0.8285    negative || 3 | 441 | 0.9932    ||======================    Precision || 0.9851 | 0.9149 |    OVERALL 0/1 ACCURACY: 0.935578    LOG LOSS/instance: 0.111003    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.881154    AUC: 0.996136      OVERALL RESULTS    ---------------------------------------    AUC: 0.996136 (0.0000)    Accuracy: 0.935578 (0.0000)    Positive precision: 0.985075 (0.0000)    Positive recall: 0.828452 (0.0000)    Negative precision: 0.914938 (0.0000)    Negative recall: 0.993243 (0.0000)    Log-loss: 0.111003 (0.0000)    Log-loss reduction: 0.881154 (0.0000)    F1 Score: 0.900000 (0.0000)    AUPRC: 0.991883 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:43 PM Time elapsed(s): 0.016      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-TrainTest-breast-cancer.withThreshold-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-TrainTest-breast-cancer.withThreshold-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-TrainTest-breast-cancer.withThreshold.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold.txt'  maml.exe Test eval=BinaryClassifier{threshold=0.95 useRawScore=-} dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.withThreshold-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 198 | 41 | 0.8285    negative || 3 | 441 | 0.9932    ||======================    Precision || 0.9851 | 0.9149 |    OVERALL 0/1 ACCURACY: 0.935578    LOG LOSS/instance: 0.111003    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.881154    AUC: 0.996136      OVERALL RESULTS    ---------------------------------------    AUC: 0.996136 (0.0000)    Accuracy: 0.935578 (0.0000)    Positive precision: 0.985075 (0.0000)    Positive recall: 0.828452 (0.0000)    Negative precision: 0.914938 (0.0000)    Negative recall: 0.993243 (0.0000)    Log-loss: 0.111003 (0.0000)    Log-loss reduction: 0.881154 (0.0000)    F1 Score: 0.900000 (0.0000)    AUPRC: 0.991883 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:43 PM Time elapsed(s): 0.01      Suffix of length 34 compared against sequence of length 42  Running 'LogisticRegression' on 'breast-cancer'  Running as: CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-CV-breast-cancer.withThreshold.txt} norm=no threads- eval=BinaryClassifier{threshold=0.95 useRawScore=-}  maml.exe CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} eval=BinaryClassifier{threshold=0.95 useRawScore=-} threads=- norm=No dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-CV-breast-cancer.withThreshold.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Not adding a normalizer.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 118 | 16 | 0.8806    negative || 3 | 217 | 0.9864    ||======================    Precision || 0.9752 | 0.9313 |    OVERALL 0/1 ACCURACY: 0.946328    LOG LOSS/instance: 0.143504    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.850048    AUC: 0.994132    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 81 | 24 | 0.7714    negative || 0 | 224 | 1.0000    ||======================    Precision || 1.0000 | 0.9032 |    OVERALL 0/1 ACCURACY: 0.927052    LOG LOSS/instance: 0.111794    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.876260    AUC: 0.997236      OVERALL RESULTS    ---------------------------------------    AUC: 0.995684 (0.0016)    Accuracy: 0.936690 (0.0096)    Positive precision: 0.987603 (0.0124)    Positive recall: 0.826013 (0.0546)    Negative precision: 0.917278 (0.0141)    Negative recall: 0.993182 (0.0068)    Log-loss: 0.127649 (0.0159)    Log-loss reduction: 0.863154 (0.0131)    F1 Score: 0.898229 (0.0273)    AUPRC: 0.991584 (0.0025)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:43 PM Time elapsed(s): 0.02      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-CV-breast-cancer.withThreshold-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-CV-breast-cancer.withThreshold-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-CV-breast-cancer.withThreshold-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-CV-breast-cancer.withThreshold-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-CV-breast-cancer.withThreshold-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-CV-breast-cancer.withThreshold-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-CV-breast-cancer.withThreshold.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-CV-breast-cancer.withThreshold.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-CV-breast-cancer.withThreshold.txt'  Test BinaryClassifierTesterThresholdingTest: completed normally: passed  Test BinaryClassifierTesterThresholdingTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiAveragerTest with memory usage 202,252,288.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiAveragerTest [FAIL]  Assert.Equal() Failure: Values differ  Expected: 0  Actual: 2  Stack Trace:  /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs(221,0): at Microsoft.ML.RunTests.BaseTestBaseline.Done()  /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs(2306,0): at Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiAveragerTest()  at System.RuntimeMethodHandle.InvokeMethod(Object target, Void** arguments, Signature sig, Boolean isConstructor)  at System.Reflection.MethodBaseInvoker.InvokeWithNoArgs(Object obj, BindingFlags invokeAttr) Starting test: Microsoft.ML.RunTests.TestPredictors.RandomCalibratorPerceptronTest  Output:  Running 'WeightedEnsembleMulticlass' on 'iris'  Running as: TrainTest tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=5 oc=MultiAverage tp=-} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt xf=Term{col=Label} out={/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Average-TrainTest-iris-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Average-TrainTest-iris.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=5 oc=MultiAverage tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Average-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Average-TrainTest-iris-model.zip seed=1 xf=Term{col=Label}    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 5 learners for the batch 1    Beginning training model 1 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 1 of 5 finished in 00:00:00.0244687    Beginning training model 2 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 2 of 5 finished in 00:00:00.0324807    Beginning training model 3 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 3 of 5 finished in 00:00:00.0244580    Beginning training model 4 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 10 of 15 weights.    Trainer 4 of 5 finished in 00:00:00.0300869    Beginning training model 5 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 5 of 5 finished in 00:00:00.0393199    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 45 | 5 | 0.9000    2 || 0 | 3 | 47 | 0.9400    ||========================    Precision ||1.0000 |0.9375 |0.9038 |    Accuracy(micro-avg): 0.946667    Accuracy(macro-avg): 0.946667    Log-loss: 0.433342    Log-loss reduction: 0.605555      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.946667 (0.0000)    Accuracy(macro-avg): 0.946667 (0.0000)    Log-loss: 0.433342 (0.0000)    Log-loss reduction: 0.605555 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:44 PM Time elapsed(s): 0.181      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Average-TrainTest-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Average-TrainTest-iris-out.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-Average-TrainTest-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Average-TrainTest-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Average-TrainTest-iris-rp.txt  *** Failure #1: Values to compare are 0.4333919882774353 and 0.43334200978279114  AllowedVariance: 1E-06  delta: 5E-05  delta2: 5E-05   Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CompareNumbersWithTolerance(Double, Double, System.Nullable`1[System.Int32], Int32, Boolean) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 663  Boolean MatchNumberWithTolerance(System.Text.RegularExpressions.MatchCollection, System.Text.RegularExpressions.MatchCollection, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 602  Boolean GetNumbersFromFile(System.String ByRef, System.String ByRef, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 581  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 556  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_TrainTest(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Boolean, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 399  Void EnsemblesMultiAveragerTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 2305  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  *** Failure #2: Output and baseline mismatch at line 3, expected '0.946667 0.946667 0.433392 0.60551 MultiAverage mlr{t-} 5 WeightedEnsembleMulticlass %Data% %Data% %Output% 99 0 0 maml.exe TrainTest test=%Data% tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=5 oc=MultiAverage tp=-} dout=%Output% data=%Data% out=%Output% seed=1 xf=Term{col=Label} /oc:MultiAverage;/bp:mlr{t-};/nm:5 ' but got '0.946667 0.946667 0.433342 0.605555 MultiAverage mlr{t-} 5 WeightedEnsembleMulticlass %Data% %Data% %Output% 99 0 0 maml.exe TrainTest test=%Data% tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=5 oc=MultiAverage tp=-} dout=%Output% data=%Data% out=%Output% seed=1 xf=Term{col=Label} /oc:MultiAverage;/bp:mlr{t-};/nm:5 ' : 'WeightedEnsembleMulticlass/WE-Average-TrainTest-iris-rp.txt'  Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 566  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_TrainTest(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Boolean, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 399  Void EnsemblesMultiAveragerTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 2305  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Average-TrainTest-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Average-TrainTest-iris.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-Average-TrainTest-iris.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Average-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Average-TrainTest-iris-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 45 | 5 | 0.9000    2 || 0 | 3 | 47 | 0.9400    ||========================    Precision ||1.0000 |0.9375 |0.9038 |    Accuracy(micro-avg): 0.946667    Accuracy(macro-avg): 0.946667    Log-loss: 0.433342    Log-loss reduction: 0.605555      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.946667 (0.0000)    Accuracy(macro-avg): 0.946667 (0.0000)    Log-loss: 0.433342 (0.0000)    Log-loss reduction: 0.605555 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:44 PM Time elapsed(s): 0.226      Suffix of length 27 compared against sequence of length 61  Test EnsemblesMultiAveragerTest: completed normally: failed  Test EnsemblesMultiAveragerTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.MulticlassifierLightGBMKeyLabelTest [SKIP]  LightGBM is 64-bit only Finished test: Microsoft.ML.RunTests.TestPredictors.RandomCalibratorPerceptronTest with memory usage 202,448,896.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.RandomCalibratorPerceptronTest [FAIL]  Assert.Equal() Failure: Values differ  Expected: 0  Actual: 2  Stack Trace:  /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs(221,0): at Microsoft.ML.RunTests.BaseTestBaseline.Done()  /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs(1639,0): at Microsoft.ML.RunTests.TestPredictors.RandomCalibratorPerceptronTest()  at System.RuntimeMethodHandle.InvokeMethod(Object target, Void** arguments, Signature sig, Boolean isConstructor)  at System.Reflection.MethodBaseInvoker.InvokeWithNoArgs(Object obj, BindingFlags invokeAttr)  Output: Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesAveragerCombinerTest  Running 'AveragedPerceptron' on 'breast-cancer'  Running as: TrainTest tr=AveragedPerceptron data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom-model.zip} dout={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom.txt} numcali=200  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=AveragedPerceptron numcali=200 dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 160 instances with missing features during training (over 10 iterations; 16 inst/iter)    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 234 | 5 | 0.9791    negative || 12 | 432 | 0.9730    ||======================    Precision || 0.9512 | 0.9886 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.120617    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.870860    AUC: 0.996146      OVERALL RESULTS    ---------------------------------------    AUC: 0.996146 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.951220 (0.0000)    Positive recall: 0.979079 (0.0000)    Negative precision: 0.988558 (0.0000)    Negative recall: 0.972973 (0.0000)    Log-loss: 0.120617 (0.0000)    Log-loss reduction: 0.870860 (0.0000)    F1 Score: 0.964948 (0.0000)    AUPRC: 0.992065 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:44 PM Time elapsed(s): 0.011      Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom-out.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom-rp.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.calibrateRandom-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 234 | 5 | 0.9791    negative || 12 | 432 | 0.9730    ||======================    Precision || 0.9512 | 0.9886 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.120617    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.870860    AUC: 0.996146      OVERALL RESULTS    ---------------------------------------    AUC: 0.996146 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.951220 (0.0000)    Positive recall: 0.979079 (0.0000)    Negative precision: 0.988558 (0.0000)    Negative recall: 0.972973 (0.0000)    Log-loss: 0.120617 (0.0000)    Log-loss reduction: 0.870860 (0.0000)    F1 Score: 0.964948 (0.0000)    AUPRC: 0.992065 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:44 PM Time elapsed(s): 0.012      Suffix of length 34 compared against sequence of length 38  Running 'AveragedPerceptron' on 'breast-cancer'  Running as: CV tr=AveragedPerceptron data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.calibrateRandom.txt} threads- numcali=200  maml.exe CV tr=AveragedPerceptron threads=- numcali=200 dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.calibrateRandom.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 80 instances with missing features during training (over 10 iterations; 8 inst/iter)    Training calibrator.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 80 instances with missing features during training (over 10 iterations; 8 inst/iter)    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 133 | 1 | 0.9925    negative || 9 | 211 | 0.9591    ||======================    Precision || 0.9366 | 0.9953 |    OVERALL 0/1 ACCURACY: 0.971751    LOG LOSS/instance: 0.139629    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.854097    AUC: 0.994403    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 100 | 5 | 0.9524    negative || 3 | 221 | 0.9866    ||======================    Precision || 0.9709 | 0.9779 |    OVERALL 0/1 ACCURACY: 0.975684    LOG LOSS/instance: 0.121001    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.866069    AUC: 0.997619      OVERALL RESULTS    ---------------------------------------    AUC: 0.996011 (0.0016)    Accuracy: 0.973718 (0.0020)    Positive precision: 0.953747 (0.0171)    Positive recall: 0.972459 (0.0201)    Negative precision: 0.986580 (0.0087)    Negative recall: 0.972849 (0.0138)    Log-loss: 0.130315 (0.0093)    Log-loss reduction: 0.860083 (0.0060)    F1 Score: 0.962653 (0.0011)    AUPRC: 0.992269 (0.0025)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266843    09/21/2026 13:02:44 PM Time elapsed(s): 0.014      Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.calibrateRandom-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer.calibrateRandom-out.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.calibrateRandom-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.calibrateRandom-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer.calibrateRandom-rp.txt  *** Failure #1: Values to compare are 0.996028 and 0.996011  AllowedVariance: 1E-07  delta: 1.7E-05  delta2: 1.7E-05   Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean MatchNumberWithTolerance(System.Text.RegularExpressions.MatchCollection, System.Text.RegularExpressions.MatchCollection, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 615  Boolean GetNumbersFromFile(System.String ByRef, System.String ByRef, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 581  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 556  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_CV(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 445  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 366  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void RandomCalibratorPerceptronTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 1638  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  *** Failure #2: Output and baseline mismatch at line 3, expected '0.996028 0.972305 0.95666 0.964996 0.981961 0.975122 0.12985 0.860569 0.960623 0.99228 AveragedPerceptron %Data% %Output% 99 0 0 maml.exe CV tr=AveragedPerceptron threads=- numcali=200 dout=%Output% data=%Data% seed=1 ' but got '0.996011 0.973718 0.953747 0.972459 0.98658 0.972849 0.130315 0.860083 0.962653 0.992269 AveragedPerceptron %Data% %Output% 99 0 0 maml.exe CV tr=AveragedPerceptron threads=- numcali=200 dout=%Output% data=%Data% seed=1 ' : 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.calibrateRandom-rp.txt'  Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 566  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_CV(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 445  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 366  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void RandomCalibratorPerceptronTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 1638  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.calibrateRandom.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer.calibrateRandom.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.calibrateRandom.txt'  Test RandomCalibratorPerceptronTest: completed normally: failed  Test RandomCalibratorPerceptronTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierFieldAwareFactorizationMachineTest [SKIP]  FieldAwareFactorizationMachine doesn't currently support non x86/x64. https://github.com/dotnet/machinelearning/issues/5871 Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesAveragerCombinerTest with memory usage 202,489,856.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesAveragerCombinerTest [PASS]  Output: Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiClassBootstrapSelectorTest  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{nm=20 oc=Average tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Average-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Average-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{nm=20 oc=Average tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Average-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Average-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 26 instances with missing features during training (over 1 iterations; 26 inst/iter)    Trainer 1 of 20 finished in 00:00:00.0017904    Beginning training model 2 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 2 of 20 finished in 00:00:00.0011659    Beginning training model 3 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 11 instances with missing features during training (over 1 iterations; 11 inst/iter)    Trainer 3 of 20 finished in 00:00:00.0006566    Beginning training model 4 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 4 of 20 finished in 00:00:00.0006683    Beginning training model 5 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 5 of 20 finished in 00:00:00.0006269    Beginning training model 6 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 6 of 20 finished in 00:00:00.0006498    Beginning training model 7 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 7 of 20 finished in 00:00:00.0006280    Beginning training model 8 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 8 of 20 finished in 00:00:00.0006092    Beginning training model 9 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 9 of 20 finished in 00:00:00.0006620    Beginning training model 10 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 10 of 20 finished in 00:00:00.0006309    Beginning training model 11 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 11 of 20 finished in 00:00:00.0006047    Beginning training model 12 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 13 instances with missing features during training (over 1 iterations; 13 inst/iter)    Trainer 12 of 20 finished in 00:00:00.0006460    Beginning training model 13 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 13 of 20 finished in 00:00:00.0006013    Beginning training model 14 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 17 instances with missing features during training (over 1 iterations; 17 inst/iter)    Trainer 14 of 20 finished in 00:00:00.0006020    Beginning training model 15 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 15 of 20 finished in 00:00:00.0006376    Beginning training model 16 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 16 of 20 finished in 00:00:00.0006118    Beginning training model 17 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 17 of 20 finished in 00:00:00.0006246    Beginning training model 18 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 19 instances with missing features during training (over 1 iterations; 19 inst/iter)    Trainer 18 of 20 finished in 00:00:00.0007089    Beginning training model 19 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 23 instances with missing features during training (over 1 iterations; 23 inst/iter)    Trainer 19 of 20 finished in 00:00:00.0005980    Beginning training model 20 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 20 of 20 finished in 00:00:00.0006459    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9585 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.116558    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.875206    AUC: 0.995920      OVERALL RESULTS    ---------------------------------------    AUC: 0.995920 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.958506 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981900 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.116558 (0.0000)    Log-loss reduction: 0.875206 (0.0000)    F1 Score: 0.962500 (0.0000)    AUPRC: 0.991714 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266851    09/21/2026 13:02:44 PM Time elapsed(s): 0.048      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Average-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Average-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-Average-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Average-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Average-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-Average-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Average-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Average-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-Average-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Average-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Average-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9585 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.116558    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.875206    AUC: 0.995920      OVERALL RESULTS    ---------------------------------------    AUC: 0.995920 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.958506 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981900 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.116558 (0.0000)    Log-loss reduction: 0.875206 (0.0000)    F1 Score: 0.962500 (0.0000)    AUPRC: 0.991714 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266851    09/21/2026 13:02:44 PM Time elapsed(s): 0.023      Suffix of length 34 compared against sequence of length 118  Test EnsemblesAveragerCombinerTest: completed normally: passed  Test EnsemblesAveragerCombinerTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiClassBootstrapSelectorTest with memory usage 204,210,176.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiClassBootstrapSelectorTest [FAIL]  Assert.Equal() Failure: Values differ  Expected: 0  Actual: 2  Stack Trace:  /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs(221,0): at Microsoft.ML.RunTests.BaseTestBaseline.Done()  /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs(2209,0): at Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiClassBootstrapSelectorTest()  at System.RuntimeMethodHandle.InvokeMethod(Object target, Void** arguments, Signature sig, Boolean isConstructor)  at System.Reflection.MethodBaseInvoker.InvokeWithNoArgs(Object obj, BindingFlags invokeAttr)  Output: Starting test: Microsoft.ML.RunTests.TestPredictors.FastTreeBinaryClassificationTest  Running 'WeightedEnsembleMulticlass' on 'iris'  Running as: TrainTest tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=20 st=BootstrapSelector{} tp=-} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt xf=Term{col=Label} out={/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=20 st=BootstrapSelector{} tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris-model.zip seed=1 xf=Term{col=Label}    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 1 of 20 finished in 00:00:00.0163051    Beginning training model 2 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 2 of 20 finished in 00:00:00.0244879    Beginning training model 3 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 3 of 20 finished in 00:00:00.0352260    Beginning training model 4 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 10 of 15 weights.    Trainer 4 of 20 finished in 00:00:00.0225311    Beginning training model 5 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 5 of 20 finished in 00:00:00.0211885    Beginning training model 6 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 6 of 20 finished in 00:00:00.0178832    Beginning training model 7 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 7 of 20 finished in 00:00:00.0229953    Beginning training model 8 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 13 of 15 weights.    Trainer 8 of 20 finished in 00:00:00.0231119    Beginning training model 9 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 9 of 20 finished in 00:00:00.0410582    Beginning training model 10 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 10 of 20 finished in 00:00:00.0216013    Beginning training model 11 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 11 of 20 finished in 00:00:00.0388651    Beginning training model 12 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 12 of 20 finished in 00:00:00.0154245    Beginning training model 13 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 10 of 15 weights.    Trainer 13 of 20 finished in 00:00:00.0126372    Beginning training model 14 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 14 of 20 finished in 00:00:00.0180484    Beginning training model 15 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 15 of 20 finished in 00:00:00.0206018    Beginning training model 16 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 16 of 20 finished in 00:00:00.0279592    Beginning training model 17 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 10 of 15 weights.    Trainer 17 of 20 finished in 00:00:00.0195145    Beginning training model 18 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 18 of 20 finished in 00:00:00.0183723    Beginning training model 19 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 19 of 20 finished in 00:00:00.0199409    Beginning training model 20 of 20    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 20 of 20 finished in 00:00:00.0249953    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 45 | 5 | 0.9000    2 || 0 | 4 | 46 | 0.9200    ||========================    Precision ||1.0000 |0.9184 |0.9020 |    Accuracy(micro-avg): 0.940000    Accuracy(macro-avg): 0.940000    Log-loss: 0.435527    Log-loss reduction: 0.603567      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.940000 (0.0000)    Accuracy(macro-avg): 0.940000 (0.0000)    Log-loss: 0.435527 (0.0000)    Log-loss reduction: 0.603567 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266851    09/21/2026 13:02:45 PM Time elapsed(s): 0.496      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Bootstrap-TrainTest-iris-out.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Bootstrap-TrainTest-iris-rp.txt  *** Failure #1: Values to compare are 0.4356130063533783 and 0.4355269968509674  AllowedVariance: 1E-06  delta: 8.6E-05  delta2: 8.6E-05   Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CompareNumbersWithTolerance(Double, Double, System.Nullable`1[System.Int32], Int32, Boolean) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 663  Boolean MatchNumberWithTolerance(System.Text.RegularExpressions.MatchCollection, System.Text.RegularExpressions.MatchCollection, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 602  Boolean GetNumbersFromFile(System.String ByRef, System.String ByRef, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 581  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 556  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_TrainTest(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Boolean, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 399  Void EnsemblesMultiClassBootstrapSelectorTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 2208  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  *** Failure #2: Output and baseline mismatch at line 3, expected '0.94 0.94 0.435613 0.603488 mlr{t-} 20 WeightedEnsembleMulticlass %Data% %Data% %Output% 99 0 0 maml.exe TrainTest test=%Data% tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=20 st=BootstrapSelector{} tp=-} dout=%Output% data=%Data% out=%Output% seed=1 xf=Term{col=Label} /bp:mlr{t-};/nm:20 ' but got '0.94 0.94 0.435527 0.603567 mlr{t-} 20 WeightedEnsembleMulticlass %Data% %Data% %Output% 99 0 0 maml.exe TrainTest test=%Data% tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=20 st=BootstrapSelector{} tp=-} dout=%Output% data=%Data% out=%Output% seed=1 xf=Term{col=Label} /bp:mlr{t-};/nm:20 ' : 'WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris-rp.txt'  Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 566  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_TrainTest(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Boolean, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 399  Void EnsemblesMultiClassBootstrapSelectorTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 2208  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Bootstrap-TrainTest-iris.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Bootstrap-TrainTest-iris-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 45 | 5 | 0.9000    2 || 0 | 4 | 46 | 0.9200    ||========================    Precision ||1.0000 |0.9184 |0.9020 |    Accuracy(micro-avg): 0.940000    Accuracy(macro-avg): 0.940000    Log-loss: 0.435527    Log-loss reduction: 0.603567      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.940000 (0.0000)    Accuracy(macro-avg): 0.940000 (0.0000)    Log-loss: 0.435527 (0.0000)    Log-loss reduction: 0.603567 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266851    09/21/2026 13:02:45 PM Time elapsed(s): 0.017      Suffix of length 27 compared against sequence of length 151  Test EnsemblesMultiClassBootstrapSelectorTest: completed normally: failed  Test EnsemblesMultiClassBootstrapSelectorTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.FastTreeBinaryClassificationTest with memory usage 205,189,120.00 and max memory usage 207,192,064.00 Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLDSvmTest  Microsoft.ML.RunTests.TestPredictors.FastTreeBinaryClassificationTest [PASS]  Output:  Running 'FastTreeBinaryClassification' on 'breast-cancer'  Running as: TrainTest tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} cache- out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255} cache=- dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Processed 683 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Reserved memory for tree learner: 3852 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 240 | 1 | 0.9959    negative || 13 | 445 | 0.9716    ||======================    Precision || 0.9486 | 0.9978 |    OVERALL 0/1 ACCURACY: 0.979971    LOG LOSS/instance: 0.092572    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.900387    AUC: 0.995370      OVERALL RESULTS    ---------------------------------------    AUC: 0.995370 (0.0000)    Accuracy: 0.979971 (0.0000)    Positive precision: 0.948617 (0.0000)    Positive recall: 0.995851 (0.0000)    Negative precision: 0.997758 (0.0000)    Negative recall: 0.971616 (0.0000)    Log-loss: 0.092572 (0.0000)    Log-loss reduction: 0.900387 (0.0000)    F1 Score: 0.971660 (0.0000)    AUPRC: 0.970606 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:45 PM Time elapsed(s): 0.041      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 240 | 1 | 0.9959    negative || 13 | 445 | 0.9716    ||======================    Precision || 0.9486 | 0.9978 |    OVERALL 0/1 ACCURACY: 0.979971    LOG LOSS/instance: 0.092572    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.900387    AUC: 0.995370      OVERALL RESULTS    ---------------------------------------    AUC: 0.995370 (0.0000)    Accuracy: 0.979971 (0.0000)    Positive precision: 0.948617 (0.0000)    Positive recall: 0.995851 (0.0000)    Negative precision: 0.997758 (0.0000)    Negative recall: 0.971616 (0.0000)    Log-loss: 0.092572 (0.0000)    Log-loss reduction: 0.900387 (0.0000)    F1 Score: 0.971660 (0.0000)    AUPRC: 0.970606 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:45 PM Time elapsed(s): 0.007      Suffix of length 33 compared against sequence of length 45  Running 'FastTreeBinaryClassification' on 'breast-cancer'  Running as: TrainTest tr=FastTreeBinaryClassification{nl=5 mil=5 tdrop=0.5 lr=0.25 iter=20 mb=255} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} cache- out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=FastTreeBinaryClassification{nl=5 mil=5 tdrop=0.5 lr=0.25 iter=20 mb=255} cache=- dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Processed 683 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Reserved memory for tree learner: 3852 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 234 | 7 | 0.9710    negative || 28 | 430 | 0.9389    ||======================    Precision || 0.8931 | 0.9840 |    OVERALL 0/1 ACCURACY: 0.949928    LOG LOSS/instance: 0.626065    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.326318    AUC: 0.987371      OVERALL RESULTS    ---------------------------------------    AUC: 0.987371 (0.0000)    Accuracy: 0.949928 (0.0000)    Positive precision: 0.893130 (0.0000)    Positive recall: 0.970954 (0.0000)    Negative precision: 0.983982 (0.0000)    Negative recall: 0.938865 (0.0000)    Log-loss: 0.626065 (0.0000)    Log-loss reduction: 0.326318 (0.0000)    F1 Score: 0.930417 (0.0000)    AUPRC: 0.942315 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:45 PM Time elapsed(s): 0.033      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDrop-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 234 | 7 | 0.9710    negative || 28 | 430 | 0.9389    ||======================    Precision || 0.8931 | 0.9840 |    OVERALL 0/1 ACCURACY: 0.949928    LOG LOSS/instance: 0.626065    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.326318    AUC: 0.987371      OVERALL RESULTS    ---------------------------------------    AUC: 0.987371 (0.0000)    Accuracy: 0.949928 (0.0000)    Positive precision: 0.893130 (0.0000)    Positive recall: 0.970954 (0.0000)    Negative precision: 0.983982 (0.0000)    Negative recall: 0.938865 (0.0000)    Log-loss: 0.626065 (0.0000)    Log-loss reduction: 0.326318 (0.0000)    F1 Score: 0.930417 (0.0000)    AUPRC: 0.942315 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:45 PM Time elapsed(s): 0.01      Suffix of length 33 compared against sequence of length 45  Running 'FastTreeBinaryClassification' on 'breast-cancer'  Running as: TrainTest tr=FastTreeBinaryClassification{nl=5 mil=5 bsr+ lr=0.25 iter=20 mb=255} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} cache- out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=FastTreeBinaryClassification{nl=5 mil=5 bsr+ lr=0.25 iter=20 mb=255} cache=- dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Processed 683 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Reserved memory for tree learner: 3852 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 233 | 8 | 0.9668    negative || 28 | 430 | 0.9389    ||======================    Precision || 0.8927 | 0.9817 |    OVERALL 0/1 ACCURACY: 0.948498    LOG LOSS/instance: 0.837162    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.099166    AUC: 0.983973      OVERALL RESULTS    ---------------------------------------    AUC: 0.983973 (0.0000)    Accuracy: 0.948498 (0.0000)    Positive precision: 0.892720 (0.0000)    Positive recall: 0.966805 (0.0000)    Negative precision: 0.981735 (0.0000)    Negative recall: 0.938865 (0.0000)    Log-loss: 0.837162 (0.0000)    Log-loss reduction: 0.099166 (0.0000)    F1 Score: 0.928287 (0.0000)    AUPRC: 0.939241 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:45 PM Time elapsed(s): 0.029      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeBsr-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 233 | 8 | 0.9668    negative || 28 | 430 | 0.9389    ||======================    Precision || 0.8927 | 0.9817 |    OVERALL 0/1 ACCURACY: 0.948498    LOG LOSS/instance: 0.837162    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.099166    AUC: 0.983973      OVERALL RESULTS    ---------------------------------------    AUC: 0.983973 (0.0000)    Accuracy: 0.948498 (0.0000)    Positive precision: 0.892720 (0.0000)    Positive recall: 0.966805 (0.0000)    Negative precision: 0.981735 (0.0000)    Negative recall: 0.938865 (0.0000)    Log-loss: 0.837162 (0.0000)    Log-loss reduction: 0.099166 (0.0000)    F1 Score: 0.928287 (0.0000)    AUPRC: 0.939241 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:45 PM Time elapsed(s): 0.009      Suffix of length 33 compared against sequence of length 45  Running 'FastTreeBinaryClassification' on 'breast-cancer'  Running as: TrainTest tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255 dt+} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} cache- out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255 dt+} cache=- dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise on disk    Warning:  16 of 699 examples will be skipped due to missing feature values    Processed 683 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise on disk    Warning:  16 of 699 examples will be skipped due to missing feature values    Reserved memory for tree learner: 3852 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 240 | 1 | 0.9959    negative || 13 | 445 | 0.9716    ||======================    Precision || 0.9486 | 0.9978 |    OVERALL 0/1 ACCURACY: 0.979971    LOG LOSS/instance: 0.092572    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.900387    AUC: 0.995370      OVERALL RESULTS    ---------------------------------------    AUC: 0.995370 (0.0000)    Accuracy: 0.979971 (0.0000)    Positive precision: 0.948617 (0.0000)    Positive recall: 0.995851 (0.0000)    Negative precision: 0.997758 (0.0000)    Negative recall: 0.971616 (0.0000)    Log-loss: 0.092572 (0.0000)    Log-loss reduction: 0.900387 (0.0000)    F1 Score: 0.971660 (0.0000)    AUPRC: 0.970606 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.048      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 240 | 1 | 0.9959    negative || 13 | 445 | 0.9716    ||======================    Precision || 0.9486 | 0.9978 |    OVERALL 0/1 ACCURACY: 0.979971    LOG LOSS/instance: 0.092572    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.900387    AUC: 0.995370      OVERALL RESULTS    ---------------------------------------    AUC: 0.995370 (0.0000)    Accuracy: 0.979971 (0.0000)    Positive precision: 0.948617 (0.0000)    Positive recall: 0.995851 (0.0000)    Negative precision: 0.997758 (0.0000)    Negative recall: 0.971616 (0.0000)    Log-loss: 0.092572 (0.0000)    Log-loss reduction: 0.900387 (0.0000)    F1 Score: 0.971660 (0.0000)    AUPRC: 0.970606 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.007      Suffix of length 33 compared against sequence of length 45  Test FastTreeBinaryClassificationTest: completed normally: passed Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLDSvmTest with memory usage 206,983,168.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLDSvmTest [FAIL]  Assert.Equal() Failure: Values differ  Expected: 0  Actual: 2  Stack Trace:  /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs(221,0): at Microsoft.ML.RunTests.BaseTestBaseline.Done()  /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs(2159,0): at Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLDSvmTest()  at System.RuntimeMethodHandle.InvokeMethod(Object target, Void** arguments, Signature sig, Boolean isConstructor)  at System.Reflection.MethodBaseInvoker.InvokeWithNoArgs(Object obj, BindingFlags invokeAttr)  Output: Starting test: Microsoft.ML.RunTests.TestPredictors.PAVCalibratorPerceptronTest  Running 'LdSvm' on 'breast-cancer'  Running as: TrainTest tr=LdSvm{iter=1000} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=LdSvm{iter=1000} dout=/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 16 rows with missing feature/label values    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 7 | 0.9707    negative || 11 | 433 | 0.9752    ||======================    Precision || 0.9547 | 0.9841 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.111359    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.880773    AUC: 0.996127      OVERALL RESULTS    ---------------------------------------    AUC: 0.996127 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.954733 (0.0000)    Positive recall: 0.970711 (0.0000)    Negative precision: 0.984091 (0.0000)    Negative recall: 0.975225 (0.0000)    Log-loss: 0.111359 (0.0000)    Log-loss reduction: 0.880773 (0.0000)    F1 Score: 0.962656 (0.0000)    AUPRC: 0.992120 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.045      Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-def-TrainTest-breast-cancer-out.txt  Output matches baseline: 'LdSvm/LDSVM-def-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-def-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'LdSvm/LDSVM-def-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-def-TrainTest-breast-cancer.txt  Output matches baseline: 'LdSvm/LDSVM-def-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 7 | 0.9707    negative || 11 | 433 | 0.9752    ||======================    Precision || 0.9547 | 0.9841 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.111359    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.880773    AUC: 0.996127      OVERALL RESULTS    ---------------------------------------    AUC: 0.996127 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.954733 (0.0000)    Positive recall: 0.970711 (0.0000)    Negative precision: 0.984091 (0.0000)    Negative recall: 0.975225 (0.0000)    Log-loss: 0.111359 (0.0000)    Log-loss reduction: 0.880773 (0.0000)    F1 Score: 0.962656 (0.0000)    AUPRC: 0.992120 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.013      Suffix of length 34 compared against sequence of length 38  Running 'LdSvm' on 'breast-cancer'  Running as: CV tr=LdSvm{iter=1000} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-CV-breast-cancer.txt} threads-  maml.exe CV tr=LdSvm{iter=1000} threads=- dout=/root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 8 rows with missing feature/label values    Training calibrator.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 8 rows with missing feature/label values    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 134 | 0 | 1.0000    negative || 10 | 210 | 0.9545    ||======================    Precision || 0.9306 | 1.0000 |    OVERALL 0/1 ACCURACY: 0.971751    LOG LOSS/instance: 0.125103    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.869275    AUC: 0.994369    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 94 | 11 | 0.8952    negative || 4 | 220 | 0.9821    ||======================    Precision || 0.9592 | 0.9524 |    OVERALL 0/1 ACCURACY: 0.954407    LOG LOSS/instance: 0.283104    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.686643    AUC: 0.951786      OVERALL RESULTS    ---------------------------------------    AUC: 0.973077 (0.0213)    Accuracy: 0.963079 (0.0087)    Positive precision: 0.944870 (0.0143)    Positive recall: 0.947619 (0.0524)    Negative precision: 0.976190 (0.0238)    Negative recall: 0.968344 (0.0138)    Log-loss: 0.204103 (0.0790)    Log-loss reduction: 0.777959 (0.0913)    F1 Score: 0.945069 (0.0190)    AUPRC: 0.974864 (0.0146)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.063      Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-def-CV-breast-cancer-out.txt  Output matches baseline: 'LdSvm/LDSVM-def-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-def-CV-breast-cancer-rp.txt  *** Failure #1: Values to compare are 0.988226 and 0.973077  AllowedVariance: 0.01  delta: 0.02  delta2: 0.02   Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean MatchNumberWithTolerance(System.Text.RegularExpressions.MatchCollection, System.Text.RegularExpressions.MatchCollection, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 615  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 556  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_CV(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 445  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 366  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void BinaryClassifierLDSvmTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 2158  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  *** Failure #2: Output and baseline mismatch at line 3, expected '0.988226 0.972305 0.945987 0.977221 0.988702 0.968344 0.147997 0.840485 0.961097 0.986066 1000 LdSvm %Data% %Output% 99 0 0 maml.exe CV tr=LdSvm{iter=1000} threads=- dout=%Output% data=%Data% seed=1 /iter:1000 ' but got '0.973077 0.963079 0.94487 0.947619 0.97619 0.968344 0.204103 0.777959 0.945069 0.974864 1000 LdSvm %Data% %Output% 99 0 0 maml.exe CV tr=LdSvm{iter=1000} threads=- dout=%Output% data=%Data% seed=1 /iter:1000 ' : 'LdSvm/LDSVM-def-CV-breast-cancer-rp.txt'  Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 566  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_CV(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 445  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 366  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void BinaryClassifierLDSvmTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 2158  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  Comparing /root/helix/work/workitem/e/TestOutput/LdSvm/LDSVM-def-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LdSvm/linux-arm64/LDSVM-def-CV-breast-cancer.txt  Output matches baseline: 'LdSvm/LDSVM-def-CV-breast-cancer.txt'  Test BinaryClassifierLDSvmTest: completed normally: failed  Test BinaryClassifierLDSvmTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.PAVCalibratorPerceptronTest with memory usage 207,020,032.00 and max memory usage 207,192,064.00  Microsoft.ML.RunTests.TestPredictors.PAVCalibratorPerceptronTest [FAIL]  Assert.Equal() Failure: Values differ  Expected: 0  Actual: 2  Stack Trace:  /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs(221,0): at Microsoft.ML.RunTests.BaseTestBaseline.Done()  /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs(1627,0): at Microsoft.ML.RunTests.TestPredictors.PAVCalibratorPerceptronTest()  at System.RuntimeMethodHandle.InvokeMethod(Object target, Void** arguments, Signature sig, Boolean isConstructor)  at System.Reflection.MethodBaseInvoker.InvokeWithNoArgs(Object obj, BindingFlags invokeAttr)  Output: Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionNormTest  Running 'AveragedPerceptron' on 'breast-cancer'  Running as: TrainTest tr=AveragedPerceptron data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration-model.zip} dout={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration.txt} cali=PAV  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=AveragedPerceptron cali=PAV dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 160 instances with missing features during training (over 10 iterations; 16 inst/iter)    Training calibrator.    PAV calibrator: piecewise function approximation has 9 components.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 234 | 5 | 0.9791    negative || 12 | 432 | 0.9730    ||======================    Precision || 0.9512 | 0.9886 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.084507    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.909522    AUC: 0.996146      OVERALL RESULTS    ---------------------------------------    AUC: 0.996146 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.951220 (0.0000)    Positive recall: 0.979079 (0.0000)    Negative precision: 0.988558 (0.0000)    Negative recall: 0.972973 (0.0000)    Log-loss: 0.084507 (0.0000)    Log-loss reduction: 0.909522 (0.0000)    F1 Score: 0.964948 (0.0000)    AUPRC: 0.992065 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.01      Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration-out.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration-rp.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.PAVcalibration-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 234 | 5 | 0.9791    negative || 12 | 432 | 0.9730    ||======================    Precision || 0.9512 | 0.9886 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.084507    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.909522    AUC: 0.996146      OVERALL RESULTS    ---------------------------------------    AUC: 0.996146 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.951220 (0.0000)    Positive recall: 0.979079 (0.0000)    Negative precision: 0.988558 (0.0000)    Negative recall: 0.972973 (0.0000)    Log-loss: 0.084507 (0.0000)    Log-loss reduction: 0.909522 (0.0000)    F1 Score: 0.964948 (0.0000)    AUPRC: 0.992065 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.006      Suffix of length 34 compared against sequence of length 39  Running 'AveragedPerceptron' on 'breast-cancer'  Running as: CV tr=AveragedPerceptron data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.PAVcalibration.txt} threads- cali=PAV  maml.exe CV tr=AveragedPerceptron threads=- cali=PAV dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.PAVcalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 80 instances with missing features during training (over 10 iterations; 8 inst/iter)    Training calibrator.    PAV calibrator: piecewise function approximation has 5 components.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 80 instances with missing features during training (over 10 iterations; 8 inst/iter)    Training calibrator.    PAV calibrator: piecewise function approximation has 6 components.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 133 | 1 | 0.9925    negative || 9 | 211 | 0.9591    ||======================    Precision || 0.9366 | 0.9953 |    OVERALL 0/1 ACCURACY: 0.971751    LOG LOSS/instance: Infinity    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): -Infinity    AUC: 0.994403    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 100 | 5 | 0.9524    negative || 3 | 221 | 0.9866    ||======================    Precision || 0.9709 | 0.9779 |    OVERALL 0/1 ACCURACY: 0.975684    LOG LOSS/instance: 0.227705    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.747961    AUC: 0.997619      OVERALL RESULTS    ---------------------------------------    AUC: 0.996011 (0.0016)    Accuracy: 0.973718 (0.0020)    Positive precision: 0.953747 (0.0171)    Positive recall: 0.972459 (0.0201)    Negative precision: 0.986580 (0.0087)    Negative recall: 0.972849 (0.0138)    Log-loss: Infinity (NaN)    Log-loss reduction: -Infinity (NaN)    F1 Score: 0.962653 (0.0011)    AUPRC: 0.992269 (0.0025)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.011      Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.PAVcalibration-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer.PAVcalibration-out.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.PAVcalibration-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.PAVcalibration-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer.PAVcalibration-rp.txt  *** Failure #1: Values to compare are 0.95666 and 0.953747  AllowedVariance: 0.001  delta: 0.003  delta2: 0.003   Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean MatchNumberWithTolerance(System.Text.RegularExpressions.MatchCollection, System.Text.RegularExpressions.MatchCollection, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 615  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 556  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_CV(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 445  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 366  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void PAVCalibratorPerceptronTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 1626  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  *** Failure #2: Output and baseline mismatch at line 3, expected '0.996028 0.972305 0.95666 0.964996 0.981961 0.975122 Infinity -Infinity 0.960623 0.99228 AveragedPerceptron %Data% %Output% 99 0 0 maml.exe CV tr=AveragedPerceptron threads=- cali=PAV dout=%Output% data=%Data% seed=1 ' but got '0.996011 0.973718 0.953747 0.972459 0.98658 0.972849 Infinity -Infinity 0.962653 0.992269 AveragedPerceptron %Data% %Output% 99 0 0 maml.exe CV tr=AveragedPerceptron threads=- cali=PAV dout=%Output% data=%Data% seed=1 ' : 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.PAVcalibration-rp.txt'  Void Fail(System.String, System.Object[]) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 244  Boolean CheckEqualityFromPathsCore(System.String, System.String, System.String, Int32, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 566  Boolean CheckEqualityCore(System.String, System.String, System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 429  Boolean CheckEqualityNormalized(System.String, System.String, System.String, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestBaseline.cs 397  Void Run(RunContext, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 212  Void Run_CV(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 445  Void RunOneAllTests(Microsoft.ML.RunTests.PredictorAndArgs, Microsoft.ML.TestFrameworkCommon.TestDataset, System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 366  Void RunAllTests(System.Collections.Generic.IList`1[Microsoft.ML.RunTests.PredictorAndArgs], System.Collections.Generic.IList`1[Microsoft.ML.TestFrameworkCommon.TestDataset], System.String[], System.String, Boolean, Int32, NumberParseOption) /__w/1/s/test/Microsoft.ML.TestFramework/BaseTestPredictorsMaml.cs 353  Void PAVCalibratorPerceptronTest() /__w/1/s/test/Microsoft.ML.Predictor.Tests/TestPredictors.cs 1626  System.Object InvokeMethod(System.Object, Void**, System.Signature, Boolean) 0  System.Object InvokeWithNoArgs(System.Object, System.Reflection.BindingFlags) 0  System.Object CallTestMethod(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 149  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 256  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task b__1() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/ExecutionTimer.cs 48  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task AggregateAsync(System.Func`1[System.Threading.Tasks.Task]) 0  System.Threading.Tasks.Task b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 215  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 90  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task RunAsync(System.Func`1[System.Threading.Tasks.Task]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 214  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) 0  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(System.Object) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestInvoker.cs 112  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 180  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Decimal] b__46_0() 0  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  System.Threading.Tasks.Task`1[System.Decimal] RunAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestInvoker.cs 163  System.Threading.Tasks.Task`1[System.Decimal] InvokeTestMethodAsync(Xunit.Sdk.ExceptionAggregator) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 88  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestRunner.cs 70  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] InvokeTestAsync(Xunit.Sdk.ExceptionAggregator) 0  System.Threading.Tasks.Task`1[System.Tuple`2[System.Decimal,System.String]] b__0() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void MoveNext() /_/src/xunit.core/Sdk/ExceptionAggregator.cs 107  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[T] RunAsync[T](System.Func`1[System.Threading.Tasks.Task`1[T]]) 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestRunner.cs 149  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestAsync() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCaseRunner.cs 140  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCaseRunner.cs 82  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync(Xunit.Abstractions.IMessageSink, Xunit.Sdk.IMessageBus, System.Object[], Xunit.Sdk.ExceptionAggregator, System.Threading.CancellationTokenSource) /_/src/xunit.execution/Sdk/Frameworks/XunitTestCase.cs 170  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCaseAsync(Xunit.Sdk.IXunitTestCase) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestMethodRunner.cs 45  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 136  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCasesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestMethodRunner.cs 106  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodAsync(Xunit.Abstractions.ITestMethod, Xunit.Abstractions.IReflectionMethodInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Object[]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestClassRunner.cs 206  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestMethodsAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestClassRunner.cs 175  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassAsync(Xunit.Abstractions.ITestClass, Xunit.Abstractions.IReflectionTypeInfo, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase]) /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestCollectionRunner.cs 185  Void MoveNext() 0  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestClassesAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/TestCollectionRunner.cs 101  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunAsync() 0  Void MoveNext() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 346  Void Start[TStateMachine](TStateMachine ByRef) 0  Void Start[TStateMachine](TStateMachine ByRef) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] RunTestCollectionAsync(Xunit.Sdk.IMessageBus, Xunit.Abstractions.ITestCollection, System.Collections.Generic.IEnumerable`1[Xunit.Sdk.IXunitTestCase], System.Threading.CancellationTokenSource) 0  System.Threading.Tasks.Task`1[Xunit.Sdk.RunSummary] b__2() /_/src/xunit.execution/Sdk/Frameworks/Runners/XunitTestAssemblyRunner.cs 250  Void InnerInvoke() 0  Void RunFromThreadPoolDispatchLoop(System.Threading.Thread, System.Threading.ExecutionContext, System.Threading.ContextCallback, System.Object) 0  Void ExecuteWithThreadLocal(System.Threading.Tasks.Task ByRef, System.Threading.Thread) 0  Boolean Dispatch() 0  Void WorkerThreadStart() 0  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.PAVcalibration.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer.PAVcalibration.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.PAVcalibration.txt'  Test PAVCalibratorPerceptronTest: completed normally: failed  Test PAVCalibratorPerceptronTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.RegressorOlsTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionNormTest with memory usage 207,564,800.00 and max memory usage 207,564,800.00 Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesStackingCombinerTest  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionNormTest [PASS]  Output:  Running 'LogisticRegression' on 'breast-cancer'  Running as: TrainTest tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 16 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 228 | 11 | 0.9540    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9620 | 0.9753 |    OVERALL 0/1 ACCURACY: 0.970717    LOG LOSS/instance: 0.119042    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.872546    AUC: 0.996108      OVERALL RESULTS    ---------------------------------------    AUC: 0.996108 (0.0000)    Accuracy: 0.970717 (0.0000)    Positive precision: 0.962025 (0.0000)    Positive recall: 0.953975 (0.0000)    Negative precision: 0.975336 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.119042 (0.0000)    Log-loss reduction: 0.872546 (0.0000)    F1 Score: 0.957983 (0.0000)    AUPRC: 0.992030 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.01      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-norm-TrainTest-breast-cancer-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-norm-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-norm-TrainTest-breast-cancer.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 228 | 11 | 0.9540    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9620 | 0.9753 |    OVERALL 0/1 ACCURACY: 0.970717    LOG LOSS/instance: 0.119042    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.872546    AUC: 0.996108      OVERALL RESULTS    ---------------------------------------    AUC: 0.996108 (0.0000)    Accuracy: 0.970717 (0.0000)    Positive precision: 0.962025 (0.0000)    Positive recall: 0.953975 (0.0000)    Negative precision: 0.975336 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.119042 (0.0000)    Log-loss reduction: 0.872546 (0.0000)    F1 Score: 0.957983 (0.0000)    AUPRC: 0.992030 (0.0000)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.007      Suffix of length 34 compared against sequence of length 42  Running 'LogisticRegression' on 'breast-cancer'  Running as: CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-CV-breast-cancer.txt} threads-  maml.exe CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} threads=- dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 8 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 129 | 5 | 0.9627    negative || 7 | 213 | 0.9682    ||======================    Precision || 0.9485 | 0.9771 |    OVERALL 0/1 ACCURACY: 0.966102    LOG LOSS/instance: 0.137058    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.856784    AUC: 0.994166    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 96 | 9 | 0.9143    negative || 3 | 221 | 0.9866    ||======================    Precision || 0.9697 | 0.9609 |    OVERALL 0/1 ACCURACY: 0.963526    LOG LOSS/instance: 0.130675    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.855361    AUC: 0.997279      OVERALL RESULTS    ---------------------------------------    AUC: 0.995722 (0.0016)    Accuracy: 0.964814 (0.0013)    Positive precision: 0.959113 (0.0106)    Positive recall: 0.938486 (0.0242)    Negative precision: 0.968967 (0.0081)    Negative recall: 0.977394 (0.0092)    Log-loss: 0.133866 (0.0032)    Log-loss reduction: 0.856072 (0.0007)    F1 Score: 0.948366 (0.0072)    AUPRC: 0.991520 (0.0025)      ---------------------------------------    Physical memory usage(MB): 197    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.026      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-norm-CV-breast-cancer-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-norm-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-norm-CV-breast-cancer-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-norm-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-norm-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-norm-CV-breast-cancer.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-norm-CV-breast-cancer.txt'  Test BinaryClassifierLogisticRegressionNormTest: completed normally: passed  Test BinaryClassifierLogisticRegressionNormTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.WeightingRegressionPredictorsTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesStackingCombinerTest with memory usage 207,704,064.00 and max memory usage 207,704,064.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesStackingCombinerTest [PASS] Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesBestPerformanceSelectorTest  Output:  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{nm=5 oc=Stacking{bp=ap} tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{nm=5 oc=Stacking{bp=ap} tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 5 learners for the batch 1    Beginning training model 1 of 5    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 1 of 5 finished in 00:00:00.0050247    Beginning training model 2 of 5    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 2 of 5 finished in 00:00:00.0014773    Beginning training model 3 of 5    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 3 of 5 finished in 00:00:00.0007733    Beginning training model 4 of 5    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 4 of 5 finished in 00:00:00.0037783    Beginning training model 5 of 5    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 5 of 5 finished in 00:00:00.0006363    The number of instances used for stacking trainer is 213    Warning:  The trainer specified for stacking wants normalization, but we do not currently allow this.    Warning:  Skipped 40 instances with missing features during training (over 10 iterations; 4 inst/iter)    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9585 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.116054    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.875745    AUC: 0.996023      OVERALL RESULTS    ---------------------------------------    AUC: 0.996023 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.958506 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981900 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.116054 (0.0000)    Log-loss reduction: 0.875745 (0.0000)    F1 Score: 0.962500 (0.0000)    AUPRC: 0.991901 (0.0000)      ---------------------------------------    Physical memory usage(MB): 198    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.048      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-StackingAP-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-StackingAP-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-StackingAP-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-StackingAP-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9585 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.116054    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.875745    AUC: 0.996023      OVERALL RESULTS    ---------------------------------------    AUC: 0.996023 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.958506 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981900 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.116054 (0.0000)    Log-loss reduction: 0.875745 (0.0000)    F1 Score: 0.962500 (0.0000)    AUPRC: 0.991901 (0.0000)      ---------------------------------------    Physical memory usage(MB): 198    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.02      Suffix of length 34 compared against sequence of length 61  Test EnsemblesStackingCombinerTest: completed normally: passed  Test EnsemblesStackingCombinerTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.MulticlassLRSparseTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesBestPerformanceSelectorTest with memory usage 209,375,232.00 and max memory usage 209,375,232.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesBestPerformanceSelectorTest [PASS]  Output:  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{nm=20 pt=BestPerformanceSelector tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{nm=20 pt=BestPerformanceSelector tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 1 of 20 finished in 00:00:00.0081434    Beginning training model 2 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 2 of 20 finished in 00:00:00.0030251    Beginning training model 3 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 3 of 20 finished in 00:00:00.0027731    Beginning training model 4 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 4 of 20 finished in 00:00:00.0012632    Beginning training model 5 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 5 of 20 finished in 00:00:00.0011272    Beginning training model 6 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 6 of 20 finished in 00:00:00.0011828    Beginning training model 7 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 7 of 20 finished in 00:00:00.0011695    Beginning training model 8 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 8 of 20 finished in 00:00:00.0016682    Beginning training model 9 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 13 instances with missing features during training (over 1 iterations; 13 inst/iter)    Trainer 9 of 20 finished in 00:00:00.0012555    Beginning training model 10 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 10 of 20 finished in 00:00:00.0020378    Beginning training model 11 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 17 instances with missing features during training (over 1 iterations; 17 inst/iter)    Trainer 11 of 20 finished in 00:00:00.0038773    Beginning training model 12 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 12 of 20 finished in 00:00:00.0022894    Beginning training model 13 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 13 of 20 finished in 00:00:00.0012469    Beginning training model 14 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 14 of 20 finished in 00:00:00.0012217    Beginning training model 15 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 19 instances with missing features during training (over 1 iterations; 19 inst/iter)    Trainer 15 of 20 finished in 00:00:00.0014400    Beginning training model 16 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 23 instances with missing features during training (over 1 iterations; 23 inst/iter)    Trainer 16 of 20 finished in 00:00:00.0020015    Beginning training model 17 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 17 of 20 finished in 00:00:00.0021194    Beginning training model 18 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 20 instances with missing features during training (over 1 iterations; 20 inst/iter)  Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesAllDataSetSelectorTest   Trainer 18 of 20 finished in 00:00:00.0042463    Beginning training model 19 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 13 instances with missing features during training (over 1 iterations; 13 inst/iter)    Trainer 19 of 20 finished in 00:00:00.0016683    Beginning training model 20 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 20 of 20 finished in 00:00:00.0012318    List of models and the metrics after sorted    | AUC(Sorted) || Name of Model |    | 0.9969167523124358 |LinearBinaryModelParameters    | 0.9966598150051388 |LinearBinaryModelParameters    | 0.9966598150051388 |LinearBinaryModelParameters    | 0.9966598150051388 |LinearBinaryModelParameters    | 0.9965313463514902 |LinearBinaryModelParameters    | 0.9964028776978417 |LinearBinaryModelParameters    | 0.9964028776978417 |LinearBinaryModelParameters    | 0.9962744090441932 |LinearBinaryModelParameters    | 0.9962744090441932 |LinearBinaryModelParameters    | 0.9961459403905447 |LinearBinaryModelParameters    | 0.9961459403905447 |LinearBinaryModelParameters    | 0.9961459403905447 |LinearBinaryModelParameters    | 0.9958890030832477 |LinearBinaryModelParameters    | 0.9957605344295992 |LinearBinaryModelParameters    | 0.9956320657759506 |LinearBinaryModelParameters    | 0.9955035971223022 |LinearBinaryModelParameters    | 0.9952466598150052 |LinearBinaryModelParameters    | 0.9947327852004111 |LinearBinaryModelParameters    | 0.994218910585817 |LinearBinaryModelParameters    | 0.9939619732785201 |LinearBinaryModelParameters    Warning:  10 of 20 trainings failed.    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 229 | 10 | 0.9582    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9622 | 0.9775 |    OVERALL 0/1 ACCURACY: 0.972182    LOG LOSS/instance: 0.117306    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.874405    AUC: 0.996042      OVERALL RESULTS    ---------------------------------------    AUC: 0.996042 (0.0000)    Accuracy: 0.972182 (0.0000)    Positive precision: 0.962185 (0.0000)    Positive recall: 0.958159 (0.0000)    Negative precision: 0.977528 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.117306 (0.0000)    Log-loss reduction: 0.874405 (0.0000)    F1 Score: 0.960168 (0.0000)    AUPRC: 0.991960 (0.0000)      ---------------------------------------    Physical memory usage(MB): 199    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.079      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-BestPerf-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-BestPerf-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-BestPerf-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-BestPerf-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 229 | 10 | 0.9582    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9622 | 0.9775 |    OVERALL 0/1 ACCURACY: 0.972182    LOG LOSS/instance: 0.117306    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.874405    AUC: 0.996042      OVERALL RESULTS    ---------------------------------------    AUC: 0.996042 (0.0000)    Accuracy: 0.972182 (0.0000)    Positive precision: 0.962185 (0.0000)    Positive recall: 0.958159 (0.0000)    Negative precision: 0.977528 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.117306 (0.0000)    Log-loss reduction: 0.874405 (0.0000)    F1 Score: 0.960168 (0.0000)    AUPRC: 0.991960 (0.0000)      ---------------------------------------    Physical memory usage(MB): 199    Virtual memory usage(MB): 266859    09/21/2026 13:02:46 PM Time elapsed(s): 0.018      Suffix of length 34 compared against sequence of length 141  Test EnsemblesBestPerformanceSelectorTest: completed normally: passed  Test EnsemblesBestPerformanceSelectorTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.MulticlassCVTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestPredictors.RegressorLightGBMMAETest [SKIP]  LightGBM is 64-bit only  Microsoft.ML.RunTests.TestPredictors.MulticlassSdcaTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestPredictors.NnConfigTests [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesAllDataSetSelectorTest with memory usage 207,114,240.00 and max memory usage 209,014,784.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesAllDataSetSelectorTest [PASS]  Output: Starting test: Microsoft.ML.RunTests.TestPredictors.FastTreeHighMinDocsTest  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{nm=20 st=AllInstanceSelector tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-All-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-All-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{nm=20 st=AllInstanceSelector tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-All-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-All-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 1 of 20 finished in 00:00:00.0006844    Beginning training model 2 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 2 of 20 finished in 00:00:00.0003081    Beginning training model 3 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 3 of 20 finished in 00:00:00.0003246    Beginning training model 4 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 4 of 20 finished in 00:00:00.0002829    Beginning training model 5 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 5 of 20 finished in 00:00:00.0002676    Beginning training model 6 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 6 of 20 finished in 00:00:00.0003034    Beginning training model 7 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 7 of 20 finished in 00:00:00.0002700    Beginning training model 8 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 8 of 20 finished in 00:00:00.0002655    Beginning training model 9 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 9 of 20 finished in 00:00:00.0002938    Beginning training model 10 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 10 of 20 finished in 00:00:00.0002695    Beginning training model 11 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 11 of 20 finished in 00:00:00.0002609    Beginning training model 12 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 12 of 20 finished in 00:00:00.0002615    Beginning training model 13 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 13 of 20 finished in 00:00:00.0002905    Beginning training model 14 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 14 of 20 finished in 00:00:00.0003445    Beginning training model 15 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 15 of 20 finished in 00:00:00.0002663    Beginning training model 16 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 16 of 20 finished in 00:00:00.0002916    Beginning training model 17 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 17 of 20 finished in 00:00:00.0002789    Beginning training model 18 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 18 of 20 finished in 00:00:00.0002659    Beginning training model 19 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 19 of 20 finished in 00:00:00.0002850    Beginning training model 20 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 20 of 20 finished in 00:00:00.0002695    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 7 | 0.9707    negative || 11 | 433 | 0.9752    ||======================    Precision || 0.9547 | 0.9841 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.117326    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.874384    AUC: 0.995995      OVERALL RESULTS    ---------------------------------------    AUC: 0.995995 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.954733 (0.0000)    Positive recall: 0.970711 (0.0000)    Negative precision: 0.984091 (0.0000)    Negative recall: 0.975225 (0.0000)    Log-loss: 0.117326 (0.0000)    Log-loss reduction: 0.874384 (0.0000)    F1 Score: 0.962656 (0.0000)    AUPRC: 0.991908 (0.0000)      ---------------------------------------    Physical memory usage(MB): 199    Virtual memory usage(MB): 266859    09/21/2026 13:02:47 PM Time elapsed(s): 0.042      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-All-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-All-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-All-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-All-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-All-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-All-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-All-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-All-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-All-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-All-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-All-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 7 | 0.9707    negative || 11 | 433 | 0.9752    ||======================    Precision || 0.9547 | 0.9841 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.117326    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.874384    AUC: 0.995995      OVERALL RESULTS    ---------------------------------------    AUC: 0.995995 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.954733 (0.0000)    Positive recall: 0.970711 (0.0000)    Negative precision: 0.984091 (0.0000)    Negative recall: 0.975225 (0.0000)    Log-loss: 0.117326 (0.0000)    Log-loss reduction: 0.874384 (0.0000)    F1 Score: 0.962656 (0.0000)    AUPRC: 0.991908 (0.0000)      ---------------------------------------    Physical memory usage(MB): 199    Virtual memory usage(MB): 266859    09/21/2026 13:02:47 PM Time elapsed(s): 0.09      Suffix of length 34 compared against sequence of length 98  Test EnsemblesAllDataSetSelectorTest: completed normally: passed  Test EnsemblesAllDataSetSelectorTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.TestMulticlassEnsembleCombiner [SKIP]  LightGBM is 64-bit only Finished test: Microsoft.ML.RunTests.TestPredictors.FastTreeHighMinDocsTest with memory usage 209,408,000.00 and max memory usage 209,408,000.00 Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryPriorTest  Microsoft.ML.RunTests.TestPredictors.FastTreeHighMinDocsTest [PASS]  Output:  Running 'FastTreeBinaryClassification' on 'breast-cancer'  Running as: TrainTest tr=FastTreeBinaryClassification{mil=10000 iter=5} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} cache- out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=FastTreeBinaryClassification{mil=10000 iter=5} cache=- dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Processed 683 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Reserved memory for tree learner: 468 bytes    Starting to train ...    Warning:  5 of the boosting iterations failed to grow a tree. This is commonly because the minimum documents in leaf hyperparameter was set too high for this dataset.    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 0 | 241 | 0.0000    negative || 0 | 458 | 1.0000    ||======================    Precision || 0.0000 | 0.6552 |    OVERALL 0/1 ACCURACY: 0.655222    LOG LOSS/instance: 1.000000    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): -0.076058    AUC: 0.500000      OVERALL RESULTS    ---------------------------------------    AUC: 0.500000 (0.0000)    Accuracy: 0.655222 (0.0000)    Positive precision: 0.000000 (0.0000)    Positive recall: 0.000000 (0.0000)    Negative precision: 0.655222 (0.0000)    Negative recall: 1.000000 (0.0000)    Log-loss: 1.000000 (0.0000)    Log-loss reduction: -0.076058 (0.0000)    F1 Score: 0.000000 (0.0000)    AUPRC: 0.415719 (0.0000)      ---------------------------------------    Physical memory usage(MB): 199    Virtual memory usage(MB): 266859    09/21/2026 13:02:47 PM Time elapsed(s): 0.029      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 0 | 241 | 0.0000    negative || 0 | 458 | 1.0000    ||======================    Precision || 0.0000 | 0.6552 |    OVERALL 0/1 ACCURACY: 0.655222    LOG LOSS/instance: 1.000000    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): -0.076058    AUC: 0.500000      OVERALL RESULTS    ---------------------------------------    AUC: 0.500000 (0.0000)    Accuracy: 0.655222 (0.0000)    Positive precision: 0.000000 (0.0000)    Positive recall: 0.000000 (0.0000)    Negative precision: 0.655222 (0.0000)    Negative recall: 1.000000 (0.0000)    Log-loss: 1.000000 (0.0000)    Log-loss reduction: -0.076058 (0.0000)    F1 Score: 0.000000 (0.0000)    AUPRC: 0.415719 (0.0000)      ---------------------------------------    Physical memory usage(MB): 199    Virtual memory usage(MB): 266859    09/21/2026 13:02:47 PM Time elapsed(s): 0.064      Suffix of length 33 compared against sequence of length 46  Test FastTreeHighMinDocsTest: completed normally: passed  Microsoft.ML.RunTests.TestPredictors.MulticlassLRTest [SKIP]  Currently flaky on non x86/x64 devices. Disabling until we figure it out. See https://github.com/dotnet/machinelearning/issues/6684 Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryPriorTest with memory usage 209,833,984.00 and max memory usage 209,833,984.00 Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionBinNormTest  Microsoft.ML.RunTests.TestPredictors.BinaryPriorTest [PASS]  Output:  Running 'PriorPredictor' on 'breast-cancer'  Running as: TrainTest tr=PriorPredictor data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:~} out={/root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=PriorPredictor dout=/root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:~} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 0 | 241 | 0.0000    negative || 0 | 458 | 1.0000    ||======================    Precision || 0.0000 | 0.6552 |    OVERALL 0/1 ACCURACY: 0.655222    LOG LOSS/instance: 0.929318    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.000000    AUC: 0.500000      OVERALL RESULTS    ---------------------------------------    AUC: 0.500000 (0.0000)    Accuracy: 0.655222 (0.0000)    Positive precision: 0.000000 (0.0000)    Positive recall: 0.000000 (0.0000)    Negative precision: 0.655222 (0.0000)    Negative recall: 1.000000 (0.0000)    Log-loss: 0.929318 (0.0000)    Log-loss reduction: 0.000000 (0.0000)    F1 Score: 0.000000 (0.0000)    AUPRC: 0.415719 (0.0000)      ---------------------------------------    Physical memory usage(MB): 199    Virtual memory usage(MB): 266859    09/21/2026 13:02:47 PM Time elapsed(s): 0.007      Comparing /root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-out.txt  Output matches baseline: 'PriorPredictor/BinaryPrior-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'PriorPredictor/BinaryPrior-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PriorPredictor/BinaryPrior-TrainTest-breast-cancer.txt  Output matches baseline: 'PriorPredictor/BinaryPrior-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 0 | 241 | 0.0000    negative || 0 | 458 | 1.0000    ||======================    Precision || 0.0000 | 0.6552 |    OVERALL 0/1 ACCURACY: 0.655222    LOG LOSS/instance: 0.929318    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.000000    AUC: 0.500000      OVERALL RESULTS    ---------------------------------------    AUC: 0.500000 (0.0000)    Accuracy: 0.655222 (0.0000)    Positive precision: 0.000000 (0.0000)    Positive recall: 0.000000 (0.0000)    Negative precision: 0.655222 (0.0000)    Negative recall: 1.000000 (0.0000)    Log-loss: 0.929318 (0.0000)    Log-loss reduction: 0.000000 (0.0000)    F1 Score: 0.000000 (0.0000)    AUPRC: 0.415719 (0.0000)      ---------------------------------------    Physical memory usage(MB): 199    Virtual memory usage(MB): 266859    09/21/2026 13:02:47 PM Time elapsed(s): 0.004      Suffix of length 33 compared against sequence of length 36  Running 'PriorPredictor' on 'breast-cancer'  Running as: CV tr=PriorPredictor data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 loader=Text{col=Label:BL:0 col=Features:~} dout={/root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-CV-breast-cancer.txt} threads-  maml.exe CV tr=PriorPredictor threads=- dout=/root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-CV-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:~} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Not adding a normalizer.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.3702 (134.0/(134.0+228.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 0 | 134 | 0.0000    negative || 0 | 228 | 1.0000    ||======================    Precision || 0.0000 | 0.6298 |    OVERALL 0/1 ACCURACY: 0.629834    LOG LOSS/instance: 0.959786    Test-set entropy (prior Log-Loss/instance): 0.950799    LOG-LOSS REDUCTION (RIG): -0.009452    AUC: 0.500000    TEST POSITIVE RATIO: 0.3175 (107.0/(107.0+230.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 0 | 107 | 0.0000    negative || 0 | 230 | 1.0000    ||======================    Precision || 0.0000 | 0.6825 |    OVERALL 0/1 ACCURACY: 0.682493    LOG LOSS/instance: 0.910421    Test-set entropy (prior Log-Loss/instance): 0.901650    LOG-LOSS REDUCTION (RIG): -0.009727    AUC: 0.500000      OVERALL RESULTS    ---------------------------------------    AUC: 0.500000 (0.0000)    Accuracy: 0.656163 (0.0263)    Positive precision: 0.000000 (0.0000)    Positive recall: 0.000000 (0.0000)    Negative precision: 0.656163 (0.0263)    Negative recall: 1.000000 (0.0000)    Log-loss: 0.935104 (0.0247)    Log-loss reduction: -0.009590 (0.0001)    F1 Score: 0.000000 (0.0000)    AUPRC: 0.418968 (0.0212)      ---------------------------------------    Physical memory usage(MB): 199    Virtual memory usage(MB): 266859    09/21/2026 13:02:47 PM Time elapsed(s): 0.012      Comparing /root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PriorPredictor/BinaryPrior-CV-breast-cancer-out.txt  Output matches baseline: 'PriorPredictor/BinaryPrior-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PriorPredictor/BinaryPrior-CV-breast-cancer-rp.txt  Output matches baseline: 'PriorPredictor/BinaryPrior-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/PriorPredictor/BinaryPrior-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PriorPredictor/BinaryPrior-CV-breast-cancer.txt  Output matches baseline: 'PriorPredictor/BinaryPrior-CV-breast-cancer.txt'  Test BinaryPriorTest: completed normally: passed Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionBinNormTest with memory usage 210,804,736.00 and max memory usage 210,804,736.00  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionBinNormTest [PASS]  Output:  Running 'LogisticRegression' on 'breast-cancer'  Running as: TrainTest tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer.txt} xf=BinNormalizer{col=Features numBins=5}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer-model.zip seed=1 xf=BinNormalizer{col=Features numBins=5}    Not adding a normalizer.    Warning:  Skipped 16 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 9 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 7 | 0.9707 Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiAveragerSDCATest    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9587 | 0.9841 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.116898    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.874842    AUC: 0.995208      OVERALL RESULTS    ---------------------------------------    AUC: 0.995208 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.958678 (0.0000)    Positive recall: 0.970711 (0.0000)    Negative precision: 0.984127 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.116898 (0.0000)    Log-loss reduction: 0.874842 (0.0000)    F1 Score: 0.964657 (0.0000)    AUPRC: 0.990065 (0.0000)      ---------------------------------------    Physical memory usage(MB): 200    Virtual memory usage(MB): 266859    09/21/2026 13:02:47 PM Time elapsed(s): 0.023      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-bin-norm-TrainTest-breast-cancer-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-bin-norm-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-bin-norm-TrainTest-breast-cancer.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 7 | 0.9707    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9587 | 0.9841 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.116898    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.874842    AUC: 0.995208      OVERALL RESULTS    ---------------------------------------    AUC: 0.995208 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.958678 (0.0000)    Positive recall: 0.970711 (0.0000)    Negative precision: 0.984127 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.116898 (0.0000)    Log-loss reduction: 0.874842 (0.0000)    F1 Score: 0.964657 (0.0000)    AUPRC: 0.990065 (0.0000)      ---------------------------------------    Physical memory usage(MB): 200    Virtual memory usage(MB): 266859    09/21/2026 13:02:47 PM Time elapsed(s): 0.012      Suffix of length 34 compared against sequence of length 42  Running 'LogisticRegression' on 'breast-cancer'  Running as: CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-CV-breast-cancer.txt} xf=BinNormalizer{col=Features numBins=5} threads-  maml.exe CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} threads=- dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 xf=BinNormalizer{col=Features numBins=5}    Not adding a normalizer.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 9 of 10 weights.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 129 | 5 | 0.9627    negative || 7 | 213 | 0.9682    ||======================    Precision || 0.9485 | 0.9771 |    OVERALL 0/1 ACCURACY: 0.966102    LOG LOSS/instance: 0.145463    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.848001    AUC: 0.992232    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 99 | 6 | 0.9429    negative || 3 | 221 | 0.9866    ||======================    Precision || 0.9706 | 0.9736 |    OVERALL 0/1 ACCURACY: 0.972644    LOG LOSS/instance: 0.123323    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.863498    AUC: 0.996769      OVERALL RESULTS    ---------------------------------------    AUC: 0.994500 (0.0023)    Accuracy: 0.969373 (0.0033)    Positive precision: 0.959559 (0.0110)    Positive recall: 0.952772 (0.0099)    Negative precision: 0.975316 (0.0017)    Negative recall: 0.977394 (0.0092)    Log-loss: 0.134393 (0.0111)    Log-loss reduction: 0.855749 (0.0077)    F1 Score: 0.956039 (0.0005)    AUPRC: 0.988987 (0.0037)      ---------------------------------------    Physical memory usage(MB): 201    Virtual memory usage(MB): 266859    09/21/2026 13:02:48 PM Time elapsed(s): 0.018      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-bin-norm-CV-breast-cancer-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-bin-norm-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-bin-norm-CV-breast-cancer-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-bin-norm-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-bin-norm-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-bin-norm-CV-breast-cancer.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-bin-norm-CV-breast-cancer.txt'  Test BinaryClassifierLogisticRegressionBinNormTest: completed normally: passed  Test BinaryClassifierLogisticRegressionBinNormTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.FastTreeRegressionTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiAveragerSDCATest with memory usage 213,606,400.00 and max memory usage 213,606,400.00 Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionNonNegativeTest  Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiAveragerSDCATest [PASS]  Output:  Running 'WeightedEnsembleMulticlass' on 'iris'  Running as: TrainTest tr=WeightedEnsembleMulticlass{bp=SDCAMC{nt=1} nm=5 oc=MultiAverage tp=-} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt xf=Term{col=Label} out={/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=WeightedEnsembleMulticlass{bp=SDCAMC{nt=1} nm=5 oc=MultiAverage tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris-model.zip seed=1 xf=Term{col=Label}    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 5 learners for the batch 1    Beginning training model 1 of 5    Using 1 thread to train.    Automatically choosing a check frequency of 1.    Auto-tuning parameters: maxIterations = 10563.    Auto-tuning parameters: L2 = 2.6670152E-05.    Auto-tuning parameters: L1Threshold (L1/L2) = 0.    Using best model from iteration 958.    Trainer 1 of 5 finished in 00:00:00.2967648    Beginning training model 2 of 5    Using 1 thread to train.    Automatically choosing a check frequency of 1.    Auto-tuning parameters: maxIterations = 8928.    Auto-tuning parameters: L2 = 2.6668373E-05.    Auto-tuning parameters: L1Threshold (L1/L2) = 0.    Using best model from iteration 874.    Trainer 2 of 5 finished in 00:00:00.1909505    Beginning training model 3 of 5    Using 1 thread to train.    Automatically choosing a check frequency of 1.    Auto-tuning parameters: maxIterations = 9201.    Auto-tuning parameters: L2 = 2.6673779E-05.    Auto-tuning parameters: L1Threshold (L1/L2) = 0.    Using best model from iteration 754.    Trainer 3 of 5 finished in 00:00:00.1548738    Beginning training model 4 of 5    Using 1 thread to train.    Automatically choosing a check frequency of 1.    Auto-tuning parameters: maxIterations = 10344.    Auto-tuning parameters: L2 = 2.66688E-05.    Auto-tuning parameters: L1Threshold (L1/L2) = 0.    Using best model from iteration 976.    Trainer 4 of 5 finished in 00:00:00.1970510    Beginning training model 5 of 5    Using 1 thread to train.    Automatically choosing a check frequency of 1.    Auto-tuning parameters: maxIterations = 9315.    Auto-tuning parameters: L2 = 2.6674597E-05.    Auto-tuning parameters: L1Threshold (L1/L2) = 0.    Using best model from iteration 1058.    Trainer 5 of 5 finished in 00:00:00.2185575    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 48 | 2 | 0.9600    2 || 0 | 1 | 49 | 0.9800    ||========================    Precision ||1.0000 |0.9796 |0.9608 |    Accuracy(micro-avg): 0.980000    Accuracy(macro-avg): 0.980000    Log-loss: 0.061647    Log-loss reduction: 0.943887      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.980000 (0.0000)    Accuracy(macro-avg): 0.980000 (0.0000)    Log-loss: 0.061647 (0.0000)    Log-loss reduction: 0.943887 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 1.078      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-SDCA-Average-TrainTest-iris-out.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-SDCA-Average-TrainTest-iris-rp.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-SDCA-Average-TrainTest-iris.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-SDCA-Average-TrainTest-iris-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 48 | 2 | 0.9600    2 || 0 | 1 | 49 | 0.9800    ||========================    Precision ||1.0000 |0.9796 |0.9608 |    Accuracy(micro-avg): 0.980000    Accuracy(macro-avg): 0.980000    Log-loss: 0.061647    Log-loss reduction: 0.943887      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.980000 (0.0000)    Accuracy(macro-avg): 0.980000 (0.0000)    Log-loss: 0.061647 (0.0000)    Log-loss reduction: 0.943887 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.016      Suffix of length 27 compared against sequence of length 71  Test EnsemblesMultiAveragerSDCATest: completed normally: passed  Test EnsemblesMultiAveragerSDCATest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.OneClassSvmLibsvmWrapperTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestPredictors.RegressorLightGBMTest [SKIP]  LightGBM is 64-bit only Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionNonNegativeTest with memory usage 212,992,000.00 and max memory usage 213,299,200.00 Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesRandomPartitionInstanceSelectorTest Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionNonNegativeTest [PASS]  Output:  Running 'LogisticRegression' on 'breast-cancer'  Running as: TrainTest tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-4 nt=1 nn=+} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer.txt} norm=no  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-4 nt=1 nn=+} norm=No dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Warning:  Skipped 16 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 228 | 11 | 0.9540    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9580 | 0.9753 |    OVERALL 0/1 ACCURACY: 0.969253    LOG LOSS/instance: 0.109007    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.883291    AUC: 0.996287      OVERALL RESULTS    ---------------------------------------    AUC: 0.996287 (0.0000)    Accuracy: 0.969253 (0.0000)    Positive precision: 0.957983 (0.0000)    Positive recall: 0.953975 (0.0000)    Negative precision: 0.975281 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.109007 (0.0000)    Log-loss reduction: 0.883291 (0.0000)    F1 Score: 0.955975 (0.0000)    AUPRC: 0.992293 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.01      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-non-negative-TrainTest-breast-cancer-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-non-negative-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-non-negative-TrainTest-breast-cancer.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 228 | 11 | 0.9540    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9580 | 0.9753 |    OVERALL 0/1 ACCURACY: 0.969253    LOG LOSS/instance: 0.109007    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.883291    AUC: 0.996287      OVERALL RESULTS    ---------------------------------------    AUC: 0.996287 (0.0000)    Accuracy: 0.969253 (0.0000)    Positive precision: 0.957983 (0.0000)    Positive recall: 0.953975 (0.0000)    Negative precision: 0.975281 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.109007 (0.0000)    Log-loss reduction: 0.883291 (0.0000)    F1 Score: 0.955975 (0.0000)    AUPRC: 0.992293 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.005      Suffix of length 34 compared against sequence of length 42  Running 'LogisticRegression' on 'breast-cancer'  Running as: CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-4 nt=1 nn=+} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-CV-breast-cancer.txt} norm=no threads-  maml.exe CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-4 nt=1 nn=+} threads=- norm=No dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Not adding a normalizer.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 9 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 129 | 5 | 0.9627    negative || 8 | 212 | 0.9636    ||======================    Precision || 0.9416 | 0.9770 |    OVERALL 0/1 ACCURACY: 0.963277    LOG LOSS/instance: 0.140964    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.852702    AUC: 0.994437    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 96 | 9 | 0.9143    negative || 3 | 221 | 0.9866    ||======================    Precision || 0.9697 | 0.9609 |    OVERALL 0/1 ACCURACY: 0.963526    LOG LOSS/instance: 0.111876    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.876169    AUC: 0.997066      OVERALL RESULTS    ---------------------------------------    AUC: 0.995752 (0.0013)    Accuracy: 0.963401 (0.0001)    Positive precision: 0.955651 (0.0140)    Positive recall: 0.938486 (0.0242)    Negative precision: 0.968914 (0.0080)    Negative recall: 0.975122 (0.0115)    Log-loss: 0.126420 (0.0145)    Log-loss reduction: 0.864435 (0.0117)    F1 Score: 0.946603 (0.0054)    AUPRC: 0.991761 (0.0020)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.021      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-non-negative-CV-breast-cancer-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-non-negative-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-non-negative-CV-breast-cancer-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-non-negative-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-non-negative-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-non-negative-CV-breast-cancer.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-non-negative-CV-breast-cancer.txt'  Test BinaryClassifierLogisticRegressionNonNegativeTest: completed normally: passed  Test BinaryClassifierLogisticRegressionNonNegativeTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesRandomPartitionInstanceSelectorTest with memory usage 213,008,384.00 and max memory usage 213,299,200.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesRandomPartitionInstanceSelectorTest [PASS] Starting test: Microsoft.ML.RunTests.TestPredictors.FastTreeBinaryClassificationNoOpGroupIdTest  Output:  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{nm=5 st=RandomPartitionSelector tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{nm=5 st=RandomPartitionSelector tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 5 learners for the batch 1    Beginning training model 1 of 5    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 4 instances with missing features during training (over 1 iterations; 4 inst/iter)    Trainer 1 of 5 finished in 00:00:00.0009211    Beginning training model 2 of 5    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 5 instances with missing features during training (over 1 iterations; 5 inst/iter)    Trainer 2 of 5 finished in 00:00:00.0003475    Beginning training model 3 of 5    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 3 instances with missing features during training (over 1 iterations; 3 inst/iter)    Trainer 3 of 5 finished in 00:00:00.0002820    Beginning training model 4 of 5    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 1 instances with missing features during training (over 1 iterations; 1 inst/iter)    Trainer 4 of 5 finished in 00:00:00.0002990    Beginning training model 5 of 5    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 3 instances with missing features during training (over 1 iterations; 3 inst/iter)    Trainer 5 of 5 finished in 00:00:00.0002508    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 235 | 4 | 0.9833    negative || 13 | 431 | 0.9707    ||======================    Precision || 0.9476 | 0.9908 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.126392    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.864677    AUC: 0.995453      OVERALL RESULTS    ---------------------------------------    AUC: 0.995453 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.947581 (0.0000)    Positive recall: 0.983264 (0.0000)    Negative precision: 0.990805 (0.0000)    Negative recall: 0.970721 (0.0000)    Log-loss: 0.126392 (0.0000)    Log-loss reduction: 0.864677 (0.0000)    F1 Score: 0.965092 (0.0000)    AUPRC: 0.990701 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.027      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-RandomPartition-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-RandomPartition-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-RandomPartition-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomPartition-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 235 | 4 | 0.9833    negative || 13 | 431 | 0.9707    ||======================    Precision || 0.9476 | 0.9908 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.126392    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.864677    AUC: 0.995453      OVERALL RESULTS    ---------------------------------------    AUC: 0.995453 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.947581 (0.0000)    Positive recall: 0.983264 (0.0000)    Negative precision: 0.990805 (0.0000)    Negative recall: 0.970721 (0.0000)    Log-loss: 0.126392 (0.0000)    Log-loss reduction: 0.864677 (0.0000)    F1 Score: 0.965092 (0.0000)    AUPRC: 0.990701 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.014      Suffix of length 34 compared against sequence of length 58  Test EnsemblesRandomPartitionInstanceSelectorTest: completed normally: passed  Test EnsemblesRandomPartitionInstanceSelectorTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.FastTreeBinaryClassificationNoOpGroupIdTest with memory usage 212,869,120.00 and max memory usage 213,299,200.00 Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierPerceptronTest  Microsoft.ML.RunTests.TestPredictors.FastTreeBinaryClassificationNoOpGroupIdTest [PASS]  Output:  Running 'FastTreeBinaryClassification' on 'breast-cancer-group'  Running as: TrainTest tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt loader=Text{col=Label:0 col=GroupId:U4[0-10]:1 col=Features:1-*} out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255} dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group.txt loader=Text{col=Label:0 col=GroupId:U4[0-10]:1 col=Features:1-*} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  This is not ranking problem, Group Id 'GroupId' column will be ignored    Warning:  Skipped 16 instances with missing features during training    Processed 683 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Warning:  This is not ranking problem, Group Id 'GroupId' column will be ignored    Warning:  Skipped 16 instances with missing features during training    Reserved memory for tree learner: 3852 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 240 | 1 | 0.9959    negative || 13 | 445 | 0.9716    ||======================    Precision || 0.9486 | 0.9978 |    OVERALL 0/1 ACCURACY: 0.979971    LOG LOSS/instance: 0.092572    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.900387    AUC: 0.995370      OVERALL RESULTS    ---------------------------------------    AUC: 0.995370 (0.0000)    Accuracy: 0.979971 (0.0000)    Positive precision: 0.948617 (0.0000)    Positive recall: 0.995851 (0.0000)    Negative precision: 0.997758 (0.0000)    Negative recall: 0.971616 (0.0000)    Log-loss: 0.092572 (0.0000)    Log-loss reduction: 0.900387 (0.0000)    F1 Score: 0.971660 (0.0000)    AUPRC: 0.970606 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.034      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-breast-cancer-group-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 240 | 1 | 0.9959    negative || 13 | 445 | 0.9716    ||======================    Precision || 0.9486 | 0.9978 |    OVERALL 0/1 ACCURACY: 0.979971    LOG LOSS/instance: 0.092572    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.900387    AUC: 0.995370      OVERALL RESULTS    ---------------------------------------    AUC: 0.995370 (0.0000)    Accuracy: 0.979971 (0.0000)    Positive precision: 0.948617 (0.0000)    Positive recall: 0.995851 (0.0000)    Negative precision: 0.997758 (0.0000)    Negative recall: 0.971616 (0.0000)    Log-loss: 0.092572 (0.0000)    Log-loss reduction: 0.900387 (0.0000)    F1 Score: 0.971660 (0.0000)    AUPRC: 0.970606 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.008      Suffix of length 33 compared against sequence of length 47  Test FastTreeBinaryClassificationNoOpGroupIdTest: completed normally: passed  Microsoft.ML.RunTests.TestPredictors.LightGBMClassificationTest [SKIP]  LightGBM is 64-bit only Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierPerceptronTest with memory usage 212,897,792.00 and max memory usage 213,299,200.00 Starting test: Microsoft.ML.RunTests.TestPredictors.TestEnsembleCombiner Microsoft.ML.RunTests.TestPredictors.BinaryClassifierPerceptronTest [PASS]  Output:  Running 'AveragedPerceptron' on 'breast-cancer'  Running as: TrainTest tr=AveragedPerceptron{lr=0.01 iter=100 lazy+} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=AveragedPerceptron{lr=0.01 iter=100 lazy+} dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 1600 instances with missing features during training (over 100 iterations; 16 inst/iter)    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 7 | 0.9707    negative || 12 | 432 | 0.9730    ||======================    Precision || 0.9508 | 0.9841 |    OVERALL 0/1 ACCURACY: 0.972182    LOG LOSS/instance: 0.115962    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.875844    AUC: 0.995995      OVERALL RESULTS    ---------------------------------------    AUC: 0.995995 (0.0000)    Accuracy: 0.972182 (0.0000)    Positive precision: 0.950820 (0.0000)    Positive recall: 0.970711 (0.0000)    Negative precision: 0.984055 (0.0000)    Negative recall: 0.972973 (0.0000)    Log-loss: 0.115962 (0.0000)    Log-loss reduction: 0.875844 (0.0000)    F1 Score: 0.960663 (0.0000)    AUPRC: 0.991840 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.017      Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer-out.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-TrainTest-breast-cancer.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 7 | 0.9707    negative || 12 | 432 | 0.9730    ||======================    Precision || 0.9508 | 0.9841 |    OVERALL 0/1 ACCURACY: 0.972182    LOG LOSS/instance: 0.115962    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.875844    AUC: 0.995995      OVERALL RESULTS    ---------------------------------------    AUC: 0.995995 (0.0000)    Accuracy: 0.972182 (0.0000)    Positive precision: 0.950820 (0.0000)    Positive recall: 0.970711 (0.0000)    Negative precision: 0.984055 (0.0000)    Negative recall: 0.972973 (0.0000)    Log-loss: 0.115962 (0.0000)    Log-loss reduction: 0.875844 (0.0000)    F1 Score: 0.960663 (0.0000)    AUPRC: 0.991840 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.005      Suffix of length 34 compared against sequence of length 38  Running 'AveragedPerceptron' on 'breast-cancer'  Running as: CV tr=AveragedPerceptron{lr=0.01 iter=100 lazy+} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.txt} threads-  maml.exe CV tr=AveragedPerceptron{lr=0.01 iter=100 lazy+} threads=- dout=/root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 800 instances with missing features during training (over 100 iterations; 8 inst/iter)    Training calibrator.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 800 instances with missing features during training (over 100 iterations; 8 inst/iter)    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 132 | 2 | 0.9851    negative || 8 | 212 | 0.9636    ||======================    Precision || 0.9429 | 0.9907 |    OVERALL 0/1 ACCURACY: 0.971751    LOG LOSS/instance: 0.136411    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.857460    AUC: 0.994199    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 98 | 7 | 0.9333    negative || 3 | 221 | 0.9866    ||======================    Precision || 0.9703 | 0.9693 |    OVERALL 0/1 ACCURACY: 0.969605    LOG LOSS/instance: 0.118826    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.868476    AUC: 0.997577      OVERALL RESULTS    ---------------------------------------    AUC: 0.995888 (0.0017)    Accuracy: 0.970678 (0.0011)    Positive precision: 0.956577 (0.0137)    Positive recall: 0.959204 (0.0259)    Negative precision: 0.979976 (0.0107)    Negative recall: 0.975122 (0.0115)    Log-loss: 0.127618 (0.0088)    Log-loss reduction: 0.862968 (0.0055)    F1 Score: 0.957480 (0.0060)    AUPRC: 0.992003 (0.0026)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266859    09/21/2026 13:02:49 PM Time elapsed(s): 0.017      Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer-out.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer-rp.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/AveragedPerceptron/linux-arm64/AveragedPerceptron-CV-breast-cancer.txt  Output matches baseline: 'AveragedPerceptron/AveragedPerceptron-CV-breast-cancer.txt'  Test BinaryClassifierPerceptronTest: completed normally: passed  Test BinaryClassifierPerceptronTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.TestEnsembleCombiner with memory usage 210,341,888.00 and max memory usage 213,299,200.00  Microsoft.ML.RunTests.TestPredictors.TestEnsembleCombiner [PASS]  Output:  Test TestEnsembleCombiner: completed normally: passed Starting test: Microsoft.ML.RunTests.TestPredictors.FastForestClassificationTest Finished test: Microsoft.ML.RunTests.TestPredictors.FastForestClassificationTest with memory usage 210,284,544.00 and max memory usage 213,299,200.00  Microsoft.ML.RunTests.TestPredictors.FastForestClassificationTest [PASS]  Output:  Running 'FastForestClassification' on 'breast-cancer'  Running as: TrainTest tr=FastForestClassification{nl=5 mil=10 iter=10} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=FastForestClassification{nl=5 mil=10 iter=10} dout=/root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Processed 683 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Reserved memory for tree learner: 3852 bytes    Starting to train ...    Training calibrator.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 234 | 7 | 0.9710    negative || 16 | 442 | 0.9651    ||======================    Precision || 0.9360 | 0.9844 |    OVERALL 0/1 ACCURACY: 0.967096    LOG LOSS/instance: 0.162280    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.825377    AUC: 0.987892      OVERALL RESULTS    ---------------------------------------    AUC: 0.987892 (0.0000)    Accuracy: 0.967096 (0.0000)    Positive precision: 0.936000 (0.0000)    Positive recall: 0.970954 (0.0000)    Negative precision: 0.984410 (0.0000)    Negative recall: 0.965066 (0.0000)    Log-loss: 0.162280 (0.0000)  Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesDefaultTest   Log-loss reduction: 0.825377 (0.0000)    F1 Score: 0.953157 (0.0000)    AUPRC: 0.957347 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:49 PM Time elapsed(s): 0.038      Comparing /root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestClassification/FastForestClassification-TrainTest-breast-cancer-out.txt  Output matches baseline: 'FastForestClassification/FastForestClassification-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestClassification/FastForestClassification-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'FastForestClassification/FastForestClassification-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestClassification/FastForestClassification-TrainTest-breast-cancer.txt  Output matches baseline: 'FastForestClassification/FastForestClassification-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 234 | 7 | 0.9710    negative || 16 | 442 | 0.9651    ||======================    Precision || 0.9360 | 0.9844 |    OVERALL 0/1 ACCURACY: 0.967096    LOG LOSS/instance: 0.162280    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.825377    AUC: 0.987892      OVERALL RESULTS    ---------------------------------------    AUC: 0.987892 (0.0000)    Accuracy: 0.967096 (0.0000)    Positive precision: 0.936000 (0.0000)    Positive recall: 0.970954 (0.0000)    Negative precision: 0.984410 (0.0000)    Negative recall: 0.965066 (0.0000)    Log-loss: 0.162280 (0.0000)    Log-loss reduction: 0.825377 (0.0000)    F1 Score: 0.953157 (0.0000)    AUPRC: 0.957347 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:49 PM Time elapsed(s): 0.006      Suffix of length 33 compared against sequence of length 45  Running 'FastForestClassification' on 'breast-cancer'  Running as: CV tr=FastForestClassification{nl=5 mil=10 iter=10} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-CV-breast-cancer.txt} threads-  maml.exe CV tr=FastForestClassification{nl=5 mil=10 iter=10} threads=- dout=/root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 8 instances with missing features during training    Processed 329 instances    Binning and forming Feature objects    Reserved memory for tree learner: 3852 bytes    Starting to train ...    Training calibrator.    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 8 instances with missing features during training    Processed 354 instances    Binning and forming Feature objects    Reserved memory for tree learner: 3816 bytes    Starting to train ...    Training calibrator.    TEST POSITIVE RATIO: 0.3702 (134.0/(134.0+228.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 127 | 7 | 0.9478    negative || 13 | 215 | 0.9430    ||======================    Precision || 0.9071 | 0.9685 |    OVERALL 0/1 ACCURACY: 0.944751    LOG LOSS/instance: 0.237138    Test-set entropy (prior Log-Loss/instance): 0.950799    LOG-LOSS REDUCTION (RIG): 0.750591    AUC: 0.980312    TEST POSITIVE RATIO: 0.3175 (107.0/(107.0+230.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 100 | 7 | 0.9346    negative || 7 | 223 | 0.9696    ||======================    Precision || 0.9346 | 0.9696 |    OVERALL 0/1 ACCURACY: 0.958457    LOG LOSS/instance: 0.153923    Test-set entropy (prior Log-Loss/instance): 0.901650    LOG-LOSS REDUCTION (RIG): 0.829288    AUC: 0.993722      OVERALL RESULTS    ---------------------------------------    AUC: 0.987017 (0.0067)    Accuracy: 0.951604 (0.0069)    Positive precision: 0.920861 (0.0137)    Positive recall: 0.941170 (0.0066)    Negative precision: 0.969017 (0.0005)    Negative recall: 0.956274 (0.0133)    Log-loss: 0.195530 (0.0416)    Log-loss reduction: 0.789939 (0.0393)    F1 Score: 0.930793 (0.0038)    AUPRC: 0.961717 (0.0240)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:50 PM Time elapsed(s): 0.042      Comparing /root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestClassification/FastForestClassification-CV-breast-cancer-out.txt  Output matches baseline: 'FastForestClassification/FastForestClassification-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestClassification/FastForestClassification-CV-breast-cancer-rp.txt  Output matches baseline: 'FastForestClassification/FastForestClassification-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastForestClassification/FastForestClassification-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastForestClassification/FastForestClassification-CV-breast-cancer.txt  Output matches baseline: 'FastForestClassification/FastForestClassification-CV-breast-cancer.txt'  Test FastForestClassificationTest: completed normally: passed Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesDefaultTest with memory usage 210,464,768.00 and max memory usage 213,299,200.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesDefaultTest [PASS]  Output:  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{nm=20 tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{nm=20 tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 26 instances with missing features during training (over 1 iterations; 26 inst/iter)    Trainer 1 of 20 finished in 00:00:00.0011178    Beginning training model 2 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 2 of 20 finished in 00:00:00.0008393    Beginning training model 3 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 11 instances with missing features during training (over 1 iterations; 11 inst/iter)    Trainer 3 of 20 finished in 00:00:00.0002691    Beginning training model 4 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 4 of 20 finished in 00:00:00.0004060    Beginning training model 5 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 5 of 20 finished in 00:00:00.0004291    Beginning training model 6 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 6 of 20 finished in 00:00:00.0003980    Beginning training model 7 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 7 of 20 finished in 00:00:00.0004120    Beginning training model 8 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 8 of 20 finished in 00:00:00.0002894    Beginning training model 9 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 9 of 20 finished in 00:00:00.0002866    Beginning training model 10 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 10 of 20 finished in 00:00:00.0003090    Beginning training model 11 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 11 of 20 finished in 00:00:00.0002830    Beginning training model 12 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 13 instances with missing features during training (over 1 iterations; 13 inst/iter)    Trainer 12 of 20 finished in 00:00:00.0002813    Beginning training model 13 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 13 of 20 finished in 00:00:00.0002786    Beginning training model 14 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 17 instances with missing features during training (over 1 iterations; 17 inst/iter)    Trainer 14 of 20 finished in 00:00:00.0002879    Beginning training model 15 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 15 of 20 finished in 00:00:00.0002783    Beginning training model 16 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 16 of 20 finished in 00:00:00.0002768    Beginning training model 17 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 17 of 20 finished in 00:00:00.0003159    Beginning training model 18 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 19 instances with missing features during training (over 1 iterations; 19 inst/iter)    Trainer 18 of 20 finished in 00:00:00.0003449    Beginning training model 19 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 23 instances with missing features during training (over 1 iterations; 23 inst/iter)    Trainer 19 of 20 finished in 00:00:00.0002726    Beginning training model 20 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 20 of 20 finished in 00:00:00.0003087    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9585 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.115894    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.875917    AUC: 0.995976      OVERALL RESULTS    ---------------------------------------    AUC: 0.995976 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.958506 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981900 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.115894 (0.0000)    Log-loss reduction: 0.875917 (0.0000)    F1 Score: 0.962500 (0.0000)    AUPRC: 0.991794 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:50 PM Time elapsed(s): 0.146      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Default-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-Default-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Default-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-Default-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Default-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-Default-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9585 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.115894    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.875917    AUC: 0.995976      OVERALL RESULTS    ---------------------------------------    AUC: 0.995976 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.958506 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981900 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.115894 (0.0000)    Log-loss reduction: 0.875917 (0.0000)    F1 Score: 0.962500 (0.0000)    AUPRC: 0.991794 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:50 PM Time elapsed(s): 0.017      Suffix of length 34 compared against sequence of length 118  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: CV tr=WeightedEnsemble{nm=20 tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-CV-breast-cancer.txt} threads- loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe CV tr=WeightedEnsemble{nm=20 tp=-} threads=- dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-CV-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 9 instances with missing features during training (over 1 iterations; 9 inst/iter)    Trainer 1 of 20 finished in 00:00:00.0019832    Beginning training model 2 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 4 instances with missing features during training (over 1 iterations; 4 inst/iter)    Trainer 2 of 20 finished in 00:00:00.0003344    Beginning training model 3 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 3 of 20 finished in 00:00:00.0003619    Beginning training model 4 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 10 instances with missing features during training (over 1 iterations; 10 inst/iter)    Trainer 4 of 20 finished in 00:00:00.0003048    Beginning training model 5 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 11 instances with missing features during training (over 1 iterations; 11 inst/iter)    Trainer 5 of 20 finished in 00:00:00.0003056    Beginning training model 6 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 9 instances with missing features during training (over 1 iterations; 9 inst/iter)    Trainer 6 of 20 finished in 00:00:00.0003394    Beginning training model 7 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 9 instances with missing features during training (over 1 iterations; 9 inst/iter)    Trainer 7 of 20 finished in 00:00:00.0003366    Beginning training model 8 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 11 instances with missing features during training (over 1 iterations; 11 inst/iter)    Trainer 8 of 20 finished in 00:00:00.0003257    Beginning training model 9 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 9 instances with missing features during training (over 1 iterations; 9 inst/iter)    Trainer 9 of 20 finished in 00:00:00.0002854    Beginning training model 10 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 7 instances with missing features during training (over 1 iterations; 7 inst/iter)    Trainer 10 of 20 finished in 00:00:00.0003455    Beginning training model 11 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 8 instances with missing features during training (over 1 iterations; 8 inst/iter)    Trainer 11 of 20 finished in 00:00:00.0003105    Beginning training model 12 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 10 instances with missing features during training (over 1 iterations; 10 inst/iter)    Trainer 12 of 20 finished in 00:00:00.0003515    Beginning training model 13 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 11 instances with missing features during training (over 1 iterations; 11 inst/iter)    Trainer 13 of 20 finished in 00:00:00.0003178    Beginning training model 14 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 8 instances with missing features during training (over 1 iterations; 8 inst/iter)    Trainer 14 of 20 finished in 00:00:00.0003026    Beginning training model 15 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 10 instances with missing features during training (over 1 iterations; 10 inst/iter)    Trainer 15 of 20 finished in 00:00:00.0003364    Beginning training model 16 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 7 instances with missing features during training (over 1 iterations; 7 inst/iter)    Trainer 16 of 20 finished in 00:00:00.0002418    Beginning training model 17 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 6 instances with missing features during training (over 1 iterations; 6 inst/iter)    Trainer 17 of 20 finished in 00:00:00.0001666    Beginning training model 18 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 10 instances with missing features during training (over 1 iterations; 10 inst/iter)    Trainer 18 of 20 finished in 00:00:00.0002043    Beginning training model 19 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 11 instances with missing features during training (over 1 iterations; 11 inst/iter)    Trainer 19 of 20 finished in 00:00:00.0002164    Beginning training model 20 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 7 instances with missing features during training (over 1 iterations; 7 inst/iter)    Trainer 20 of 20 finished in 00:00:00.0001708    Training calibrator.    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 13 instances with missing features during training (over 1 iterations; 13 inst/iter)    Trainer 1 of 20 finished in 00:00:00.0010566    Beginning training model 2 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 8 instances with missing features during training (over 1 iterations; 8 inst/iter)    Trainer 2 of 20 finished in 00:00:00.0003188    Beginning training model 3 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 7 instances with missing features during training (over 1 iterations; 7 inst/iter)    Trainer 3 of 20 finished in 00:00:00.0003197    Beginning training model 4 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 8 instances with missing features during training (over 1 iterations; 8 inst/iter)    Trainer 4 of 20 finished in 00:00:00.0002981    Beginning training model 5 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 6 instances with missing features during training (over 1 iterations; 6 inst/iter)    Trainer 5 of 20 finished in 00:00:00.0001865    Beginning training model 6 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 7 instances with missing features during training (over 1 iterations; 7 inst/iter)    Trainer 6 of 20 finished in 00:00:00.0001646    Beginning training model 7 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 8 instances with missing features during training (over 1 iterations; 8 inst/iter)    Trainer 7 of 20 finished in 00:00:00.0001702    Beginning training model 8 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 8 of 20 finished in 00:00:00.0001660    Beginning training model 9 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 7 instances with missing features during training (over 1 iterations; 7 inst/iter)    Trainer 9 of 20 finished in 00:00:00.0004241    Beginning training model 10 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 4 instances with missing features during training (over 1 iterations; 4 inst/iter)    Trainer 10 of 20 finished in 00:00:00.0003087    Beginning training model 11 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 6 instances with missing features during training (over 1 iterations; 6 inst/iter)    Trainer 11 of 20 finished in 00:00:00.0003284    Beginning training model 12 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 6 instances with missing features during training (over 1 iterations; 6 inst/iter)    Trainer 12 of 20 finished in 00:00:00.0001803    Beginning training model 13 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 11 instances with missing features during training (over 1 iterations; 11 inst/iter)    Trainer 13 of 20 finished in 00:00:00.0001698    Beginning training model 14 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 8 instances with missing features during training (over 1 iterations; 8 inst/iter)    Trainer 14 of 20 finished in 00:00:00.0001894    Beginning training model 15 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 9 instances with missing features during training (over 1 iterations; 9 inst/iter)    Trainer 15 of 20 finished in 00:00:00.0004081    Beginning training model 16 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 13 instances with missing features during training (over 1 iterations; 13 inst/iter)    Trainer 16 of 20 finished in 00:00:00.0003137    Beginning training model 17 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 7 instances with missing features during training (over 1 iterations; 7 inst/iter)    Trainer 17 of 20 finished in 00:00:00.0001901    Beginning training model 18 of 20  Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiVotingCombinerTest   Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 5 instances with missing features during training (over 1 iterations; 5 inst/iter)    Trainer 18 of 20 finished in 00:00:00.0002290    Beginning training model 19 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 8 instances with missing features during training (over 1 iterations; 8 inst/iter)    Trainer 19 of 20 finished in 00:00:00.0001883    Beginning training model 20 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 10 instances with missing features during training (over 1 iterations; 10 inst/iter)    Trainer 20 of 20 finished in 00:00:00.0001693    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 129 | 5 | 0.9627    negative || 7 | 213 | 0.9682    ||======================    Precision || 0.9485 | 0.9771 |    OVERALL 0/1 ACCURACY: 0.966102    LOG LOSS/instance: 0.143167    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.850400    AUC: 0.993996    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 103 | 2 | 0.9810    negative || 4 | 220 | 0.9821    ||======================    Precision || 0.9626 | 0.9910 |    OVERALL 0/1 ACCURACY: 0.981763    LOG LOSS/instance: 0.115437    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.872227    AUC: 0.997832      OVERALL RESULTS    ---------------------------------------    AUC: 0.995914 (0.0019)    Accuracy: 0.973932 (0.0078)    Positive precision: 0.955573 (0.0070)    Positive recall: 0.971819 (0.0091)    Negative precision: 0.984028 (0.0070)    Negative recall: 0.975162 (0.0070)    Log-loss: 0.129302 (0.0139)    Log-loss reduction: 0.861313 (0.0109)    F1 Score: 0.963627 (0.0081)    AUPRC: 0.992159 (0.0031)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:50 PM Time elapsed(s): 0.058      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Default-CV-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-Default-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Default-CV-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-Default-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Default-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Default-CV-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-Default-CV-breast-cancer.txt'  Test EnsemblesDefaultTest: completed normally: passed  Test EnsemblesDefaultTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.FastTreeRegressionCategoricalSplitTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiVotingCombinerTest with memory usage 210,608,128.00 and max memory usage 213,299,200.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiVotingCombinerTest [PASS]  Output:  Running 'WeightedEnsembleMulticlass' on 'iris'  Running as: TrainTest tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=5 oc=MultiVoting tp=-} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt xf=Term{col=Label} out={/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=5 oc=MultiVoting tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris-model.zip seed=1 xf=Term{col=Label}    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 5 learners for the batch 1    Beginning training model 1 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 1 of 5 finished in 00:00:00.0060748    Beginning training model 2 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.   Starting test: Microsoft.ML.RunTests.TestPredictors.FastTreeBinaryClassificationCategoricalSplitTest  Trainer 2 of 5 finished in 00:00:00.0087561    Beginning training model 3 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 3 of 5 finished in 00:00:00.0065847    Beginning training model 4 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 10 of 15 weights.    Trainer 4 of 5 finished in 00:00:00.0252316    Beginning training model 5 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 5 of 5 finished in 00:00:00.0073875    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 44 | 6 | 0.8800    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9565 |0.8889 |    Accuracy(micro-avg): 0.946667    Accuracy(macro-avg): 0.946667    Log-loss: 0.511576    Log-loss reduction: 0.534344      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.946667 (0.0000)    Accuracy(macro-avg): 0.946667 (0.0000)    Log-loss: 0.511576 (0.0000)    Log-loss reduction: 0.534344 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:50 PM Time elapsed(s): 0.07      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Voting-TrainTest-iris-out.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Voting-TrainTest-iris-rp.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Voting-TrainTest-iris.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Voting-TrainTest-iris-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 44 | 6 | 0.8800    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9565 |0.8889 |    Accuracy(micro-avg): 0.946667    Accuracy(macro-avg): 0.946667    Log-loss: 0.511576    Log-loss reduction: 0.534344      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.946667 (0.0000)    Accuracy(macro-avg): 0.946667 (0.0000)    Log-loss: 0.511576 (0.0000)    Log-loss reduction: 0.534344 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:50 PM Time elapsed(s): 0.009      Suffix of length 27 compared against sequence of length 61  Test EnsemblesMultiVotingCombinerTest: completed normally: passed  Test EnsemblesMultiVotingCombinerTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.WeightingClassificationFastRankPredictorsTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.FastTreeBinaryClassificationCategoricalSplitTest with memory usage 189,009,920.00 and max memory usage 213,299,200.00  Microsoft.ML.RunTests.TestPredictors.FastTreeBinaryClassificationCategoricalSplitTest [PASS]  Output: Starting test: Microsoft.ML.RunTests.TestPredictors.NoCalibratorLinearSvmTest  Running 'FastTreeBinaryClassification' on 'Census-Cat-Only'  Running as: TrainTest tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt seed=1 test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt loader=Text{header+ col=Label:0 col=Cat:TX:1-8} xf=Cat{col=Cat} xf=Concat{col=Features:Cat} out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255} dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat.txt loader=Text{header+ col=Label:0 col=Cat:TX:1-8} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-model.zip seed=1 xf=Cat{col=Cat} xf=Concat{col=Features:Cat}    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 500 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Reserved memory for tree learner: 3180 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 55 | 60 | 0.4783    negative || 17 | 368 | 0.9558    ||======================    Precision || 0.7639 | 0.8598 |    OVERALL 0/1 ACCURACY: 0.846000    LOG LOSS/instance: 0.481805    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.380722    AUC: 0.893281      OVERALL RESULTS    ---------------------------------------    AUC: 0.893281 (0.0000)    Accuracy: 0.846000 (0.0000)    Positive precision: 0.763889 (0.0000)    Positive recall: 0.478261 (0.0000)    Negative precision: 0.859813 (0.0000)    Negative recall: 0.955844 (0.0000)    Log-loss: 0.481805 (0.0000)    Log-loss reduction: 0.380722 (0.0000)    F1 Score: 0.588235 (0.0000)    AUPRC: 0.738040 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:50 PM Time elapsed(s): 0.06      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-out.txt'  Saving summary with: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-summary.txt}  Saving ini file: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-summary.txt} ini={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat.ini}  Saving predictor summary    Saving predictor as ini    Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-summary.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-summary.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-summary.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat.ini and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat.ini  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat.ini'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat.txt data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census-Cat-Only.Cat-model.zip seed=1    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 55 | 60 | 0.4783    negative || 17 | 368 | 0.9558    ||======================    Precision || 0.7639 | 0.8598 |    OVERALL 0/1 ACCURACY: 0.846000    LOG LOSS/instance: 0.481805    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.380722    AUC: 0.893281      OVERALL RESULTS    ---------------------------------------    AUC: 0.893281 (0.0000)    Accuracy: 0.846000 (0.0000)    Positive precision: 0.763889 (0.0000)    Positive recall: 0.478261 (0.0000)    Negative precision: 0.859813 (0.0000)    Negative recall: 0.955844 (0.0000)    Log-loss: 0.481805 (0.0000)    Log-loss reduction: 0.380722 (0.0000)    F1 Score: 0.588235 (0.0000)    AUPRC: 0.738040 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:50 PM Time elapsed(s): 0.01      Suffix of length 33 compared against sequence of length 43  Running 'FastTreeBinaryClassification' on 'Census'  Running as: TrainTest tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt seed=1 test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt loader=Text{header+ col=Label:0 col=Num:9-14 col=Cat:TX:1-8} xf=Cat{col=Cat} xf=Concat{col=Features:Num,Cat} out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255} dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat.txt loader=Text{header+ col=Label:0 col=Num:9-14 col=Cat:TX:1-8} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-model.zip seed=1 xf=Cat{col=Cat} xf=Concat{col=Features:Num,Cat}    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 500 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Reserved memory for tree learner: 18324 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 75 | 40 | 0.6522    negative || 6 | 379 | 0.9844    ||======================    Precision || 0.9259 | 0.9045 |    OVERALL 0/1 ACCURACY: 0.908000    LOG LOSS/instance: 0.353688    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.545395    AUC: 0.958893      OVERALL RESULTS    ---------------------------------------    AUC: 0.958893 (0.0000)    Accuracy: 0.908000 (0.0000)    Positive precision: 0.925926 (0.0000)    Positive recall: 0.652174 (0.0000)    Negative precision: 0.904535 (0.0000)    Negative recall: 0.984416 (0.0000)    Log-loss: 0.353688 (0.0000)    Log-loss reduction: 0.545395 (0.0000)    F1 Score: 0.765306 (0.0000)    AUPRC: 0.895540 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:50 PM Time elapsed(s): 0.045      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-out.txt'  Saving summary with: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-summary.txt}  Saving ini file: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-summary.txt} ini={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat.ini}  Saving predictor summary    Saving predictor as ini    Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-summary.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-summary.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-summary.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat.ini and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat.ini  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat.ini'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat.txt data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTree-TrainTest-Census.Cat-model.zip seed=1    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 75 | 40 | 0.6522    negative || 6 | 379 | 0.9844    ||======================    Precision || 0.9259 | 0.9045 |    OVERALL 0/1 ACCURACY: 0.908000    LOG LOSS/instance: 0.353688    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.545395    AUC: 0.958893      OVERALL RESULTS    ---------------------------------------    AUC: 0.958893 (0.0000)    Accuracy: 0.908000 (0.0000)    Positive precision: 0.925926 (0.0000)    Positive recall: 0.652174 (0.0000)    Negative precision: 0.904535 (0.0000)    Negative recall: 0.984416 (0.0000)    Log-loss: 0.353688 (0.0000)    Log-loss reduction: 0.545395 (0.0000)    F1 Score: 0.765306 (0.0000)    AUPRC: 0.895540 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:50 PM Time elapsed(s): 0.017      Suffix of length 33 compared against sequence of length 43  Running 'FastTreeBinaryClassification' on 'Census-Cat-Only'  Running as: TrainTest tr=FastTreeBinaryClassification{cat=+ nl=5 mil=5 lr=0.25 iter=20 mb=255} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt seed=1 test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt loader=Text{header+ col=Label:0 col=Cat:TX:1-8} xf=Cat{col=Cat} xf=Concat{col=Features:Cat} out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt tr=FastTreeBinaryClassification{cat=+ nl=5 mil=5 lr=0.25 iter=20 mb=255} dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat.txt loader=Text{header+ col=Label:0 col=Cat:TX:1-8} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-model.zip seed=1 xf=Cat{col=Cat} xf=Concat{col=Features:Cat}    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 500 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Reserved memory for tree learner: 3180 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 67 | 48 | 0.5826    negative || 18 | 367 | 0.9532    ||======================    Precision || 0.7882 | 0.8843 |    OVERALL 0/1 ACCURACY: 0.868000    LOG LOSS/instance: 0.439868    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.434625    AUC: 0.916804      OVERALL RESULTS    ---------------------------------------    AUC: 0.916804 (0.0000)    Accuracy: 0.868000 (0.0000)    Positive precision: 0.788235 (0.0000)    Positive recall: 0.582609 (0.0000)    Negative precision: 0.884337 (0.0000)    Negative recall: 0.953247 (0.0000)    Log-loss: 0.439868 (0.0000)    Log-loss reduction: 0.434625 (0.0000)    F1 Score: 0.670000 (0.0000)    AUPRC: 0.770221 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:51 PM Time elapsed(s): 0.041      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-out.txt'  Saving summary with: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-summary.txt}  Saving ini file: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-summary.txt} ini={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat.ini}  Saving predictor summary    Saving predictor as ini    Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-summary.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-summary.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-summary.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat.ini and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat.ini  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat.ini'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat.txt data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census-Cat-Only.Cat-model.zip seed=1    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 67 | 48 | 0.5826    negative || 18 | 367 | 0.9532    ||======================    Precision || 0.7882 | 0.8843 |    OVERALL 0/1 ACCURACY: 0.868000    LOG LOSS/instance: 0.439868    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.434625    AUC: 0.916804      OVERALL RESULTS    ---------------------------------------    AUC: 0.916804 (0.0000)    Accuracy: 0.868000 (0.0000)    Positive precision: 0.788235 (0.0000)    Positive recall: 0.582609 (0.0000)    Negative precision: 0.884337 (0.0000)    Negative recall: 0.953247 (0.0000)    Log-loss: 0.439868 (0.0000)    Log-loss reduction: 0.434625 (0.0000)    F1 Score: 0.670000 (0.0000)    AUPRC: 0.770221 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:51 PM Time elapsed(s): 0.008      Suffix of length 33 compared against sequence of length 43  Running 'FastTreeBinaryClassification' on 'Census'  Running as: TrainTest tr=FastTreeBinaryClassification{cat=+ nl=5 mil=5 lr=0.25 iter=20 mb=255} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt seed=1 test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt loader=Text{header+ col=Label:0 col=Num:9-14 col=Cat:TX:1-8} xf=Cat{col=Cat} xf=Concat{col=Features:Num,Cat} out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt tr=FastTreeBinaryClassification{cat=+ nl=5 mil=5 lr=0.25 iter=20 mb=255} dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat.txt loader=Text{header+ col=Label:0 col=Num:9-14 col=Cat:TX:1-8} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-model.zip seed=1 xf=Cat{col=Cat} xf=Concat{col=Features:Num,Cat}    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 500 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise    Reserved memory for tree learner: 18324 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 83 | 32 | 0.7217    negative || 11 | 374 | 0.9714    ||======================    Precision || 0.8830 | 0.9212 |    OVERALL 0/1 ACCURACY: 0.914000    LOG LOSS/instance: 0.327460    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.579106    AUC: 0.965037      OVERALL RESULTS    ---------------------------------------    AUC: 0.965037 (0.0000)    Accuracy: 0.914000 (0.0000)    Positive precision: 0.882979 (0.0000)    Positive recall: 0.721739 (0.0000)    Negative precision: 0.921182 (0.0000)    Negative recall: 0.971429 (0.0000)    Log-loss: 0.327460 (0.0000)    Log-loss reduction: 0.579106 (0.0000)    F1 Score: 0.794258 (0.0000)    AUPRC: 0.907541 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:51 PM Time elapsed(s): 0.036      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-out.txt'  Saving summary with: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-summary.txt}  Saving ini file: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-summary.txt} ini={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat.ini}  Saving predictor summary    Saving predictor as ini    Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-summary.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-summary.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-summary.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat.ini and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat.ini  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat.ini'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat.txt data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategorical-TrainTest-Census.Cat-model.zip seed=1    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 83 | 32 | 0.7217    negative || 11 | 374 | 0.9714    ||======================    Precision || 0.8830 | 0.9212 |    OVERALL 0/1 ACCURACY: 0.914000    LOG LOSS/instance: 0.327460    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.579106    AUC: 0.965037      OVERALL RESULTS    ---------------------------------------    AUC: 0.965037 (0.0000)    Accuracy: 0.914000 (0.0000)    Positive precision: 0.882979 (0.0000)    Positive recall: 0.721739 (0.0000)    Negative precision: 0.921182 (0.0000)    Negative recall: 0.971429 (0.0000)    Log-loss: 0.327460 (0.0000)    Log-loss reduction: 0.579106 (0.0000)    F1 Score: 0.794258 (0.0000)    AUPRC: 0.907541 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:51 PM Time elapsed(s): 0.007      Suffix of length 33 compared against sequence of length 43  Running 'FastTreeBinaryClassification' on 'Census-Cat-Only'  Running as: TrainTest tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255 dt+} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt seed=1 test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt loader=Text{header+ col=Label:0 col=Cat:TX:1-8} xf=Cat{col=Cat} xf=Concat{col=Features:Cat} out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255 dt+} dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat.txt loader=Text{header+ col=Label:0 col=Cat:TX:1-8} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-model.zip seed=1 xf=Cat{col=Cat} xf=Concat{col=Features:Cat}    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise on disk    Processed 500 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise on disk    Reserved memory for tree learner: 11232 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 55 | 60 | 0.4783    negative || 17 | 368 | 0.9558    ||======================    Precision || 0.7639 | 0.8598 |    OVERALL 0/1 ACCURACY: 0.846000    LOG LOSS/instance: 0.481805    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.380722    AUC: 0.893281      OVERALL RESULTS    ---------------------------------------    AUC: 0.893281 (0.0000)    Accuracy: 0.846000 (0.0000)    Positive precision: 0.763889 (0.0000)    Positive recall: 0.478261 (0.0000)    Negative precision: 0.859813 (0.0000)    Negative recall: 0.955844 (0.0000)    Log-loss: 0.481805 (0.0000)    Log-loss reduction: 0.380722 (0.0000)    F1 Score: 0.588235 (0.0000)    AUPRC: 0.738040 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:51 PM Time elapsed(s): 0.113      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-out.txt'  Saving summary with: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-summary.txt}  Saving ini file: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-summary.txt} ini={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat.ini}  Saving predictor summary    Saving predictor as ini    Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-summary.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-summary.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-summary.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat.ini and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat.ini  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat.ini'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat.txt data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census-Cat-Only.Cat-model.zip seed=1    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 55 | 60 | 0.4783    negative || 17 | 368 | 0.9558    ||======================    Precision || 0.7639 | 0.8598 |    OVERALL 0/1 ACCURACY: 0.846000    LOG LOSS/instance: 0.481805    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.380722    AUC: 0.893281      OVERALL RESULTS    ---------------------------------------    AUC: 0.893281 (0.0000)    Accuracy: 0.846000 (0.0000)    Positive precision: 0.763889 (0.0000)    Positive recall: 0.478261 (0.0000)    Negative precision: 0.859813 (0.0000)    Negative recall: 0.955844 (0.0000)    Log-loss: 0.481805 (0.0000)    Log-loss reduction: 0.380722 (0.0000)    F1 Score: 0.588235 (0.0000)    AUPRC: 0.738040 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:51 PM Time elapsed(s): 0.007      Suffix of length 33 compared against sequence of length 43  Running 'FastTreeBinaryClassification' on 'Census'  Running as: TrainTest tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255 dt+} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt seed=1 test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt loader=Text{header+ col=Label:0 col=Num:9-14 col=Cat:TX:1-8} xf=Cat{col=Cat} xf=Concat{col=Features:Num,Cat} out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt tr=FastTreeBinaryClassification{nl=5 mil=5 lr=0.25 iter=20 mb=255 dt+} dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat.txt loader=Text{header+ col=Label:0 col=Num:9-14 col=Cat:TX:1-8} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-model.zip seed=1 xf=Cat{col=Cat} xf=Concat{col=Features:Num,Cat}    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise on disk    Processed 500 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise on disk    Reserved memory for tree learner: 26424 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 75 | 40 | 0.6522    negative || 6 | 379 | 0.9844    ||======================    Precision || 0.9259 | 0.9045 |    OVERALL 0/1 ACCURACY: 0.908000    LOG LOSS/instance: 0.353688    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.545395    AUC: 0.958893      OVERALL RESULTS    ---------------------------------------    AUC: 0.958893 (0.0000)    Accuracy: 0.908000 (0.0000)    Positive precision: 0.925926 (0.0000)    Positive recall: 0.652174 (0.0000)    Negative precision: 0.904535 (0.0000)    Negative recall: 0.984416 (0.0000)    Log-loss: 0.353688 (0.0000)    Log-loss reduction: 0.545395 (0.0000)    F1 Score: 0.765306 (0.0000)    AUPRC: 0.895540 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:51 PM Time elapsed(s): 0.117      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-out.txt'  Saving summary with: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-summary.txt}  Saving ini file: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-summary.txt} ini={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat.ini}  Saving predictor summary    Saving predictor as ini    Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-summary.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-summary.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-summary.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat.ini and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat.ini  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat.ini'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat.txt data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeDisk-TrainTest-Census.Cat-model.zip seed=1    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 75 | 40 | 0.6522    negative || 6 | 379 | 0.9844    ||======================    Precision || 0.9259 | 0.9045 |    OVERALL 0/1 ACCURACY: 0.908000    LOG LOSS/instance: 0.353688    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.545395    AUC: 0.958893      OVERALL RESULTS    ---------------------------------------    AUC: 0.958893 (0.0000)    Accuracy: 0.908000 (0.0000)    Positive precision: 0.925926 (0.0000)    Positive recall: 0.652174 (0.0000)    Negative precision: 0.904535 (0.0000)    Negative recall: 0.984416 (0.0000)    Log-loss: 0.353688 (0.0000)    Log-loss reduction: 0.545395 (0.0000)    F1 Score: 0.765306 (0.0000)    AUPRC: 0.895540 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:51 PM Time elapsed(s): 0.01      Suffix of length 33 compared against sequence of length 43  Running 'FastTreeBinaryClassification' on 'Census-Cat-Only'  Running as: TrainTest tr=FastTreeBinaryClassification{cat=+ nl=5 mil=5 lr=0.25 iter=20 mb=255 dt+} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt seed=1 test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt loader=Text{header+ col=Label:0 col=Cat:TX:1-8} xf=Cat{col=Cat} xf=Concat{col=Features:Cat} out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt tr=FastTreeBinaryClassification{cat=+ nl=5 mil=5 lr=0.25 iter=20 mb=255 dt+} dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat.txt loader=Text{header+ col=Label:0 col=Cat:TX:1-8} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-model.zip seed=1 xf=Cat{col=Cat} xf=Concat{col=Features:Cat}    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise on disk    Processed 500 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise on disk    Reserved memory for tree learner: 4152 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 68 | 47 | 0.5913    negative || 16 | 369 | 0.9584    ||======================    Precision || 0.8095 | 0.8870 |    OVERALL 0/1 ACCURACY: 0.874000    LOG LOSS/instance: 0.425411    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.453207    AUC: 0.923817      OVERALL RESULTS    ---------------------------------------    AUC: 0.923817 (0.0000)    Accuracy: 0.874000 (0.0000)    Positive precision: 0.809524 (0.0000)    Positive recall: 0.591304 (0.0000)    Negative precision: 0.887019 (0.0000)    Negative recall: 0.958442 (0.0000)    Log-loss: 0.425411 (0.0000)    Log-loss reduction: 0.453207 (0.0000)    F1 Score: 0.683417 (0.0000)    AUPRC: 0.792176 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:51 PM Time elapsed(s): 0.107      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-out.txt'  Saving summary with: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-summary.txt}  Saving ini file: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-summary.txt} ini={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat.ini}  Saving predictor summary    Saving predictor as ini    Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-summary.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-summary.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-summary.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat.ini and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat.ini  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat.ini'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat.txt data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census-Cat-Only.Cat-model.zip seed=1    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 68 | 47 | 0.5913    negative || 16 | 369 | 0.9584    ||======================    Precision || 0.8095 | 0.8870 |    OVERALL 0/1 ACCURACY: 0.874000    LOG LOSS/instance: 0.425411    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.453207    AUC: 0.923817      OVERALL RESULTS    ---------------------------------------    AUC: 0.923817 (0.0000)    Accuracy: 0.874000 (0.0000)    Positive precision: 0.809524 (0.0000)    Positive recall: 0.591304 (0.0000)    Negative precision: 0.887019 (0.0000)    Negative recall: 0.958442 (0.0000)    Log-loss: 0.425411 (0.0000)    Log-loss reduction: 0.453207 (0.0000)    F1 Score: 0.683417 (0.0000)    AUPRC: 0.792176 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:51 PM Time elapsed(s): 0.009      Suffix of length 33 compared against sequence of length 43  Running 'FastTreeBinaryClassification' on 'Census'  Running as: TrainTest tr=FastTreeBinaryClassification{cat=+ nl=5 mil=5 lr=0.25 iter=20 mb=255 dt+} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt seed=1 test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt loader=Text{header+ col=Label:0 col=Num:9-14 col=Cat:TX:1-8} xf=Cat{col=Cat} xf=Concat{col=Features:Num,Cat} out={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-model.zip} dout={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt tr=FastTreeBinaryClassification{cat=+ nl=5 mil=5 lr=0.25 iter=20 mb=255 dt+} dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat.txt loader=Text{header+ col=Label:0 col=Num:9-14 col=Cat:TX:1-8} data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt out=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-model.zip seed=1 xf=Cat{col=Cat} xf=Concat{col=Features:Num,Cat}    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise on disk    Processed 500 instances    Binning and forming Feature objects    Changing data from row-wise to column-wise on disk    Reserved memory for tree learner: 19344 bytes    Starting to train ...    Not training a calibrator because it is not needed.    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 84 | 31 | 0.7304    negative || 10 | 375 | 0.9740    ||======================    Precision || 0.8936 | 0.9236 |    OVERALL 0/1 ACCURACY: 0.918000    LOG LOSS/instance: 0.322363    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.585658    AUC: 0.965624      OVERALL RESULTS    ---------------------------------------    AUC: 0.965624 (0.0000)    Accuracy: 0.918000 (0.0000)    Positive precision: 0.893617 (0.0000)    Positive recall: 0.730435 (0.0000)    Negative precision: 0.923645 (0.0000)    Negative recall: 0.974026 (0.0000)    Log-loss: 0.322363 (0.0000)    Log-loss reduction: 0.585658 (0.0000)    F1 Score: 0.803828 (0.0000)    AUPRC: 0.910384 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.091      Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-out.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-out.txt'  Saving summary with: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-summary.txt}  Saving ini file: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-model.zip} sum={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-summary.txt} ini={/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat.ini}  Saving predictor summary    Saving predictor as ini    Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-summary.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-summary.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-summary.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat.ini and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat.ini  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat.ini'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-rp.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat.txt and /root/helix/work/correlation/test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat.txt  Output matches baseline: 'FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat.txt data=/root/helix/work/correlation/test/data/adult.tiny.with-schema.txt in=/root/helix/work/workitem/e/TestOutput/FastTreeBinaryClassification/FastTreeCategoricalDisk-TrainTest-Census.Cat-model.zip seed=1    TEST POSITIVE RATIO: 0.2300 (115.0/(115.0+385.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 84 | 31 | 0.7304    negative || 10 | 375 | 0.9740    ||======================    Precision || 0.8936 | 0.9236 |    OVERALL 0/1 ACCURACY: 0.918000    LOG LOSS/instance: 0.322363    Test-set entropy (prior Log-Loss/instance): 0.778011    LOG-LOSS REDUCTION (RIG): 0.585658    AUC: 0.965624      OVERALL RESULTS    ---------------------------------------    AUC: 0.965624 (0.0000)    Accuracy: 0.918000 (0.0000)    Positive precision: 0.893617 (0.0000)    Positive recall: 0.730435 (0.0000)    Negative precision: 0.923645 (0.0000)    Negative recall: 0.974026 (0.0000)    Log-loss: 0.322363 (0.0000)    Log-loss reduction: 0.585658 (0.0000)    F1 Score: 0.803828 (0.0000)    AUPRC: 0.910384 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.008      Suffix of length 33 compared against sequence of length 43  Test FastTreeBinaryClassificationCategoricalSplitTest: completed normally: passed Finished test: Microsoft.ML.RunTests.TestPredictors.NoCalibratorLinearSvmTest with memory usage 189,042,688.00 and max memory usage 213,299,200.00  Microsoft.ML.RunTests.TestPredictors.NoCalibratorLinearSvmTest [PASS]  Output:  Running 'LinearSVM' on 'breast-cancer'  Running as: TrainTest tr=LinearSVM{iter=100 lambda=0.03} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration-model.zip} dout={/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration.txt} cali={}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=LinearSVM{iter=100 lambda=0.03} cali={} dout=/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 1600 instances with missing features during training (over 100 iterations; 16 inst/iter)    Not training a calibrator because a valid calibrator trainer was not provided.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 226 | 13 | 0.9456    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9617 | 0.9710 |    OVERALL 0/1 ACCURACY: 0.967789    LOG LOSS/instance: NaN    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.000000    AUC: 0.995797      OVERALL RESULTS    --------------------------------------- Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesBaseLearnerTest    AUC: 0.995797 (0.0000)    Accuracy: 0.967789 (0.0000)    Positive precision: 0.961702 (0.0000)    Positive recall: 0.945607 (0.0000)    Negative precision: 0.970982 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: NaN (0.0000)    Log-loss reduction: 0.000000 (0.0000)    F1 Score: 0.953586 (0.0000)    AUPRC: 0.991453 (0.0000)      ---------------------------------------    Warning:  Data does not contain a probability column. Will not output the Log-loss column    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.016      Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration-out.txt  Output matches baseline: 'LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration-rp.txt  Output matches baseline: 'LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration.txt  Output matches baseline: 'LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-TrainTest-breast-cancer.nocalibration-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 226 | 13 | 0.9456    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9617 | 0.9710 |    OVERALL 0/1 ACCURACY: 0.967789    LOG LOSS/instance: NaN    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.000000    AUC: 0.995797      OVERALL RESULTS    ---------------------------------------    AUC: 0.995797 (0.0000)    Accuracy: 0.967789 (0.0000)    Positive precision: 0.961702 (0.0000)    Positive recall: 0.945607 (0.0000)    Negative precision: 0.970982 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: NaN (0.0000)    Log-loss reduction: 0.000000 (0.0000)    F1 Score: 0.953586 (0.0000)    AUPRC: 0.991453 (0.0000)      ---------------------------------------    Warning:  Data does not contain a probability column. Will not output the Log-loss column    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.004      Suffix of length 35 compared against sequence of length 39  Running 'LinearSVM' on 'breast-cancer'  Running as: CV tr=LinearSVM{iter=100 lambda=0.03} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-CV-breast-cancer.nocalibration.txt} threads- cali={}  maml.exe CV tr=LinearSVM{iter=100 lambda=0.03} threads=- cali={} dout=/root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-CV-breast-cancer.nocalibration.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 800 instances with missing features during training (over 100 iterations; 8 inst/iter)    Not training a calibrator because a valid calibrator trainer was not provided.    Warning:  Data does not contain a probability column. Will not output the Log-loss column    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Warning:  Skipped 800 instances with missing features during training (over 100 iterations; 8 inst/iter)    Not training a calibrator because a valid calibrator trainer was not provided.    Warning:  Data does not contain a probability column. Will not output the Log-loss column    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 128 | 6 | 0.9552    negative || 7 | 213 | 0.9682    ||======================    Precision || 0.9481 | 0.9726 |    OVERALL 0/1 ACCURACY: 0.963277    LOG LOSS/instance: NaN    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.000000    AUC: 0.994233    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 97 | 8 | 0.9238    negative || 2 | 222 | 0.9911    ||======================    Precision || 0.9798 | 0.9652 |    OVERALL 0/1 ACCURACY: 0.969605    LOG LOSS/instance: NaN    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.000000    AUC: 0.997491      OVERALL RESULTS    ---------------------------------------    AUC: 0.995862 (0.0016)    Accuracy: 0.966441 (0.0032)    Positive precision: 0.963973 (0.0158)    Positive recall: 0.939517 (0.0157)    Negative precision: 0.968910 (0.0037)    Negative recall: 0.979627 (0.0114)    Log-loss: NaN (NaN)    Log-loss reduction: 0.000000 (0.0000)    F1 Score: 0.951327 (0.0003)    AUPRC: 0.991949 (0.0025)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.017      Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-CV-breast-cancer.nocalibration-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-CV-breast-cancer.nocalibration-out.txt  Output matches baseline: 'LinearSVM/LinearSVM-CV-breast-cancer.nocalibration-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-CV-breast-cancer.nocalibration-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-CV-breast-cancer.nocalibration-rp.txt  Output matches baseline: 'LinearSVM/LinearSVM-CV-breast-cancer.nocalibration-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LinearSVM/LinearSVM-CV-breast-cancer.nocalibration.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LinearSVM/LinearSVM-CV-breast-cancer.nocalibration.txt  Output matches baseline: 'LinearSVM/LinearSVM-CV-breast-cancer.nocalibration.txt'  Test NoCalibratorLinearSvmTest: completed normally: passed Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesBaseLearnerTest with memory usage 200,925,184.00 and max memory usage 213,299,200.00 Starting test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionTest  Microsoft.ML.RunTests.TestPredictors.EnsemblesBaseLearnerTest [PASS]  Output:  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{bp=AvgPer nm=3 tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{bp=AvgPer nm=3 tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 3 learners for the batch 1    Beginning training model 1 of 3    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 260 instances with missing features during training (over 10 iterations; 26 inst/iter)    Trainer 1 of 3 finished in 00:00:00.0027536    Beginning training model 2 of 3    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 150 instances with missing features during training (over 10 iterations; 15 inst/iter)    Trainer 2 of 3 finished in 00:00:00.0015553    Beginning training model 3 of 3    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 110 instances with missing features during training (over 10 iterations; 11 inst/iter)    Trainer 3 of 3 finished in 00:00:00.0021040    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9585 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.112168    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.879907    AUC: 0.996240      OVERALL RESULTS    ---------------------------------------    AUC: 0.996240 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.958506 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981900 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.112168 (0.0000)    Log-loss reduction: 0.879907 (0.0000)    F1 Score: 0.962500 (0.0000)    AUPRC: 0.992400 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.03      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-AvgPer-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-AvgPer-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-AvgPer-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-AvgPer-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9585 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.112168    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.879907    AUC: 0.996240      OVERALL RESULTS    ---------------------------------------    AUC: 0.996240 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.958506 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981900 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.112168 (0.0000)    Log-loss reduction: 0.879907 (0.0000)    F1 Score: 0.962500 (0.0000)    AUPRC: 0.992400 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.025      Suffix of length 34 compared against sequence of length 50  Test EnsemblesBaseLearnerTest: completed normally: passed  Test EnsemblesBaseLearnerTest is using linux-arm64 configuration specific baselines.  Microsoft.ML.RunTests.TestPredictors.KMeansClusteringTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionTest with memory usage 201,674,752.00 and max memory usage 213,299,200.00  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLogisticRegressionTest [PASS]  Output:  Running 'LogisticRegression' on 'breast-cancer'  Running as: TrainTest tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.txt} norm=no  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} norm=No dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Warning:  Skipped 16 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 228 | 11 | 0.9540    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9580 | 0.9753 |    OVERALL 0/1 ACCURACY: 0.969253    LOG LOSS/instance: 0.111003    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.881154    AUC: 0.996136      OVERALL RESULTS    ---------------------------------------  Starting test: Microsoft.ML.RunTests.TestPredictors.MulticlassReductionTest   AUC: 0.996136 (0.0000)    Accuracy: 0.969253 (0.0000)    Positive precision: 0.957983 (0.0000)    Positive recall: 0.953975 (0.0000)    Negative precision: 0.975281 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.111003 (0.0000)    Log-loss reduction: 0.881154 (0.0000)    F1 Score: 0.955975 (0.0000)    AUPRC: 0.991883 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.009      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-TrainTest-breast-cancer-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-TrainTest-breast-cancer-out.txt'  Saving summary with: SavePredictorAs in={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer-model.zip} sum={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer-summary.txt}  Saving predictor summary    Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer-summary.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-TrainTest-breast-cancer-summary.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-TrainTest-breast-cancer-summary.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-TrainTest-breast-cancer.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 228 | 11 | 0.9540    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9580 | 0.9753 |    OVERALL 0/1 ACCURACY: 0.969253    LOG LOSS/instance: 0.111003    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.881154    AUC: 0.996136      OVERALL RESULTS    ---------------------------------------    AUC: 0.996136 (0.0000)    Accuracy: 0.969253 (0.0000)    Positive precision: 0.957983 (0.0000)    Positive recall: 0.953975 (0.0000)    Negative precision: 0.975281 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.111003 (0.0000)    Log-loss reduction: 0.881154 (0.0000)    F1 Score: 0.955975 (0.0000)    AUPRC: 0.991883 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.004      Suffix of length 34 compared against sequence of length 42  Running 'LogisticRegression' on 'breast-cancer'  Running as: CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 dout={/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-CV-breast-cancer.txt} norm=no threads-  maml.exe CV tr=LogisticRegression{l1=1.0 l2=0.1 ot=1e-3 nt=1} threads=- norm=No dout=/root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-CV-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Not adding a normalizer.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Warning:  Skipped 8 instances with missing features/label/weight during training    Beginning optimization    num vars: 10    improvement criterion: Mean Improvement    L1 regularization selected 10 of 10 weights.    Not training a calibrator because it is not needed.    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3785 (134.0/(134.0+220.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 130 | 4 | 0.9701    negative || 7 | 213 | 0.9682    ||======================    Precision || 0.9489 | 0.9816 |    OVERALL 0/1 ACCURACY: 0.968927    LOG LOSS/instance: 0.143504    Test-set entropy (prior Log-Loss/instance): 0.956998    LOG-LOSS REDUCTION (RIG): 0.850048    AUC: 0.994132    Warning:  The predictor produced non-finite prediction values on 8 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3191 (105.0/(105.0+224.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 96 | 9 | 0.9143    negative || 3 | 221 | 0.9866    ||======================    Precision || 0.9697 | 0.9609 |    OVERALL 0/1 ACCURACY: 0.963526    LOG LOSS/instance: 0.111794    Test-set entropy (prior Log-Loss/instance): 0.903454    LOG-LOSS REDUCTION (RIG): 0.876260    AUC: 0.997236      OVERALL RESULTS    ---------------------------------------    AUC: 0.995684 (0.0016)    Accuracy: 0.966226 (0.0027)    Positive precision: 0.959301 (0.0104)    Positive recall: 0.942217 (0.0279)    Negative precision: 0.971218 (0.0103)    Negative recall: 0.977394 (0.0092)    Log-loss: 0.127649 (0.0159)    Log-loss reduction: 0.863154 (0.0131)    F1 Score: 0.950293 (0.0091)    AUPRC: 0.991584 (0.0025)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.011      Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-CV-breast-cancer-out.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-CV-breast-cancer-rp.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/LogisticRegression/LogisticRegression-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/LogisticRegression/linux-arm64/LogisticRegression-CV-breast-cancer.txt  Output matches baseline: 'LogisticRegression/LogisticRegression-CV-breast-cancer.txt'  Test BinaryClassifierLogisticRegressionTest: completed normally: passed  Test BinaryClassifierLogisticRegressionTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.MulticlassReductionTest with memory usage 202,469,376.00 and max memory usage 213,299,200.00  Microsoft.ML.RunTests.TestPredictors.MulticlassReductionTest [PASS] Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesHeterogeneousTest  Output:  Running 'OVA' on 'iris'  Running as: TrainTest tr=OVA{p=AvgPer{ lr=0.8 }} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt xf=Term{col=Label} out={/root/helix/work/workitem/e/TestOutput/OVA/OVA-TrainTest-iris-model.zip} dout={/root/helix/work/workitem/e/TestOutput/OVA/OVA-TrainTest-iris.txt} norm=no  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=OVA{p=AvgPer{ lr=0.8 }} norm=No dout=/root/helix/work/workitem/e/TestOutput/OVA/OVA-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/OVA/OVA-TrainTest-iris-model.zip seed=1 xf=Term{col=Label}    Not adding a normalizer.    Training learner 0    Training calibrator.    Training learner 1    Training calibrator.    Training learner 2    Training calibrator.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 46 | 4 | 0.9200    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9583 |0.9231 |    Accuracy(micro-avg): 0.960000    Accuracy(macro-avg): 0.960000    Log-loss: 0.254771    Log-loss reduction: 0.768097      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.960000 (0.0000)    Accuracy(macro-avg): 0.960000 (0.0000)    Log-loss: 0.254771 (0.0000)    Log-loss reduction: 0.768097 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.026      Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-TrainTest-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-TrainTest-iris-out.txt  Output matches baseline: 'OVA/OVA-TrainTest-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-TrainTest-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-TrainTest-iris-rp.txt  Output matches baseline: 'OVA/OVA-TrainTest-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-TrainTest-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-TrainTest-iris.txt  Output matches baseline: 'OVA/OVA-TrainTest-iris.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/OVA/OVA-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/OVA/OVA-TrainTest-iris-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 46 | 4 | 0.9200    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9583 |0.9231 |    Accuracy(micro-avg): 0.960000    Accuracy(macro-avg): 0.960000    Log-loss: 0.254771    Log-loss reduction: 0.768097      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.960000 (0.0000)    Accuracy(macro-avg): 0.960000 (0.0000)    Log-loss: 0.254771 (0.0000)    Log-loss reduction: 0.768097 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:52 PM Time elapsed(s): 0.01      Suffix of length 27 compared against sequence of length 36  Running 'OVA' on 'iris'  Running as: CV tr=OVA{p=AvgPer{ lr=0.8 }} data=/root/helix/work/correlation/test/data/iris.txt seed=1 xf=Term{col=Label} dout={/root/helix/work/workitem/e/TestOutput/OVA/OVA-CV-iris.txt} norm=no threads-  maml.exe CV tr=OVA{p=AvgPer{ lr=0.8 }} threads=- norm=No dout=/root/helix/work/workitem/e/TestOutput/OVA/OVA-CV-iris.txt data=/root/helix/work/correlation/test/data/iris.txt seed=1 xf=Term{col=Label}    Not adding a normalizer.    Training learner 0    Training calibrator.    Training learner 1    Training calibrator.    Training learner 2    Training calibrator.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Training learner 0    Training calibrator.    Training learner 1    Training calibrator.    Training learner 2    Training calibrator.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 21 | 0 | 0 | 1.0000    1 || 0 | 28 | 2 | 0.9333    2 || 0 | 0 | 28 | 1.0000    ||========================    Precision ||1.0000 |1.0000 |0.9333 |    Accuracy(micro-avg): 0.974684    Accuracy(macro-avg): 0.977778    Log-loss: 0.352944    Log-loss reduction: 0.675458      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 29 | 0 | 0 | 1.0000    1 || 0 | 18 | 2 | 0.9000    2 || 0 | 0 | 22 | 1.0000    ||========================    Precision ||1.0000 |1.0000 |0.9167 |    Accuracy(micro-avg): 0.971831    Accuracy(macro-avg): 0.966667    Log-loss: 0.273754    Log-loss reduction: 0.747843      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.973257 (0.0014)    Accuracy(macro-avg): 0.972222 (0.0056)    Log-loss: 0.313349 (0.0396)    Log-loss reduction: 0.711651 (0.0362)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.027      Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-CV-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-CV-iris-out.txt  Output matches baseline: 'OVA/OVA-CV-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-CV-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-CV-iris-rp.txt  Output matches baseline: 'OVA/OVA-CV-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-CV-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-CV-iris.txt  Output matches baseline: 'OVA/OVA-CV-iris.txt'  Running 'OVA' on 'iris'  Running as: TrainTest tr=OVA{p=FastForest{ }} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt xf=Term{col=Label} out={/root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-TrainTest-iris-model.zip} dout={/root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-TrainTest-iris.txt} norm=no  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=OVA{p=FastForest{ }} norm=No dout=/root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-TrainTest-iris-model.zip seed=1 xf=Term{col=Label}    Not adding a normalizer.    Training learner 0    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 150 instances    Binning and forming Feature objects    Reserved memory for tree learner: 20436 bytes    Starting to train ...    Warning:  2 of the boosting iterations failed to grow a tree. This is commonly because the minimum documents in leaf hyperparameter was set too high for this dataset.    Training calibrator.    Training learner 1    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 150 instances    Binning and forming Feature objects    Reserved memory for tree learner: 20436 bytes    Starting to train ...    Warning:  3 of the boosting iterations failed to grow a tree. This is commonly because the minimum documents in leaf hyperparameter was set too high for this dataset.    Training calibrator.    Training learner 2    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 150 instances    Binning and forming Feature objects    Reserved memory for tree learner: 20436 bytes    Starting to train ...    Warning:  1 of the boosting iterations failed to grow a tree. This is commonly because the minimum documents in leaf hyperparameter was set too high for this dataset.    Training calibrator.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 48 | 2 | 0.9600    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9600 |0.9600 |    Accuracy(micro-avg): 0.973333    Accuracy(macro-avg): 0.973333    Log-loss: 0.088201    Log-loss reduction: 0.919716      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.973333 (0.0000)    Accuracy(macro-avg): 0.973333 (0.0000)    Log-loss: 0.088201 (0.0000)    Log-loss reduction: 0.919716 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.082      Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-TrainTest-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-FastForest-TrainTest-iris-out.txt  Output matches baseline: 'OVA/OVA-FastForest-TrainTest-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-TrainTest-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-FastForest-TrainTest-iris-rp.txt  Output matches baseline: 'OVA/OVA-FastForest-TrainTest-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-TrainTest-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-FastForest-TrainTest-iris.txt  Output matches baseline: 'OVA/OVA-FastForest-TrainTest-iris.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-TrainTest-iris-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 48 | 2 | 0.9600    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9600 |0.9600 |    Accuracy(micro-avg): 0.973333    Accuracy(macro-avg): 0.973333    Log-loss: 0.088201    Log-loss reduction: 0.919716      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.973333 (0.0000)    Accuracy(macro-avg): 0.973333 (0.0000)    Log-loss: 0.088201 (0.0000)    Log-loss reduction: 0.919716 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.011      Suffix of length 27 compared against sequence of length 57  Running 'OVA' on 'iris'  Running as: CV tr=OVA{p=FastForest{ }} data=/root/helix/work/correlation/test/data/iris.txt seed=1 xf=Term{col=Label} dout={/root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-CV-iris.txt} norm=no threads-  maml.exe CV tr=OVA{p=FastForest{ }} threads=- norm=No dout=/root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-CV-iris.txt data=/root/helix/work/correlation/test/data/iris.txt seed=1 xf=Term{col=Label}    Not adding a normalizer.    Training learner 0    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 71 instances    Binning and forming Feature objects    Reserved memory for tree learner: 16380 bytes    Starting to train ...    Warning:  2 of the boosting iterations failed to grow a tree. This is commonly because the minimum documents in leaf hyperparameter was set too high for this dataset.    Training calibrator.    Training learner 1    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 71 instances    Binning and forming Feature objects    Reserved memory for tree learner: 16380 bytes    Starting to train ...    Warning:  3 of the boosting iterations failed to grow a tree. This is commonly because the minimum documents in leaf hyperparameter was set too high for this dataset.    Training calibrator.    Training learner 2    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 71 instances    Binning and forming Feature objects    Reserved memory for tree learner: 16380 bytes    Starting to train ...    Warning:  1 of the boosting iterations failed to grow a tree. This is commonly because the minimum documents in leaf hyperparameter was set too high for this dataset.    Training calibrator.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Training learner 0    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 79 instances    Binning and forming Feature objects    Reserved memory for tree learner: 17472 bytes    Starting to train ...    Warning:  2 of the boosting iterations failed to grow a tree. This is commonly because the minimum documents in leaf hyperparameter was set too high for this dataset.    Training calibrator.    Training learner 1    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 79 instances    Binning and forming Feature objects    Reserved memory for tree learner: 17472 bytes    Starting to train ...    Warning:  3 of the boosting iterations failed to grow a tree. This is commonly because the minimum documents in leaf hyperparameter was set too high for this dataset.    Training calibrator.    Training learner 2    Making per-feature arrays    Changing data from row-wise to column-wise    Processed 79 instances    Binning and forming Feature objects    Reserved memory for tree learner: 17472 bytes    Starting to train ...    Warning:  1 of the boosting iterations failed to grow a tree. This is commonly because the minimum documents in leaf hyperparameter was set too high for this dataset.    Training calibrator.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 21 | 0 | 0 | 1.0000    1 || 0 | 25 | 5 | 0.8333    2 || 0 | 1 | 27 | 0.9643    ||========================    Precision ||1.0000 |0.9615 |0.8438 |    Accuracy(micro-avg): 0.924051    Accuracy(macro-avg): 0.932540    Log-loss: 0.197783    Log-loss reduction: 0.818133      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 29 | 0 | 0 | 1.0000    1 || 0 | 19 | 1 | 0.9500    2 || 0 | 2 | 20 | 0.9091    ||========================    Precision ||1.0000 |0.9048 |0.9524 |    Accuracy(micro-avg): 0.957746    Accuracy(macro-avg): 0.953030    Log-loss: 0.103360    Log-loss reduction: 0.904794      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.940899 (0.0168)    Accuracy(macro-avg): 0.942785 (0.0102)    Log-loss: 0.150571 (0.0472)    Log-loss reduction: 0.861464 (0.0433)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.118      Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-CV-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-FastForest-CV-iris-out.txt  Output matches baseline: 'OVA/OVA-FastForest-CV-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-CV-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-FastForest-CV-iris-rp.txt  Output matches baseline: 'OVA/OVA-FastForest-CV-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/OVA/OVA-FastForest-CV-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/OVA/OVA-FastForest-CV-iris.txt  Output matches baseline: 'OVA/OVA-FastForest-CV-iris.txt'  Running 'PKPD' on 'iris'  Running as: TrainTest tr=PKPD{p=AvgPer { lr=0.8 }} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt xf=Term{col=Label} out={/root/helix/work/workitem/e/TestOutput/PKPD/PKPD-TrainTest-iris-model.zip} dout={/root/helix/work/workitem/e/TestOutput/PKPD/PKPD-TrainTest-iris.txt} norm=no  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=PKPD{p=AvgPer { lr=0.8 }} norm=No dout=/root/helix/work/workitem/e/TestOutput/PKPD/PKPD-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/PKPD/PKPD-TrainTest-iris-model.zip seed=1 xf=Term{col=Label}    Not adding a normalizer.    Training learner (0,0)    Training calibrator.    Training learner (1,0)    Training calibrator.    Training learner (1,1)    Training calibrator.    Training learner (2,0)    Training calibrator.    Training learner (2,1)    Training calibrator.    Training learner (2,2)    Training calibrator.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 46 | 4 | 0.9200    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9583 |0.9231 |    Accuracy(micro-avg): 0.960000    Accuracy(macro-avg): 0.960000    Log-loss: 0.255665    Log-loss reduction: 0.767284      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.960000 (0.0000)    Accuracy(macro-avg): 0.960000 (0.0000)    Log-loss: 0.255665 (0.0000)    Log-loss reduction: 0.767284 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.033      Comparing /root/helix/work/workitem/e/TestOutput/PKPD/PKPD-TrainTest-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PKPD/PKPD-TrainTest-iris-out.txt  Output matches baseline: 'PKPD/PKPD-TrainTest-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/PKPD/PKPD-TrainTest-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PKPD/PKPD-TrainTest-iris-rp.txt  Output matches baseline: 'PKPD/PKPD-TrainTest-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/PKPD/PKPD-TrainTest-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PKPD/PKPD-TrainTest-iris.txt  Output matches baseline: 'PKPD/PKPD-TrainTest-iris.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/PKPD/PKPD-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/PKPD/PKPD-TrainTest-iris-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 46 | 4 | 0.9200    2 || 0 | 2 | 48 | 0.9600    ||========================    Precision ||1.0000 |0.9583 |0.9231 |    Accuracy(micro-avg): 0.960000    Accuracy(macro-avg): 0.960000    Log-loss: 0.255665    Log-loss reduction: 0.767284      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.960000 (0.0000)    Accuracy(macro-avg): 0.960000 (0.0000)    Log-loss: 0.255665 (0.0000)    Log-loss reduction: 0.767284 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.012      Suffix of length 27 compared against sequence of length 42  Running 'PKPD' on 'iris'  Running as: CV tr=PKPD{p=AvgPer { lr=0.8 }} data=/root/helix/work/correlation/test/data/iris.txt seed=1 xf=Term{col=Label} dout={/root/helix/work/workitem/e/TestOutput/PKPD/PKPD-CV-iris.txt} norm=no threads-  maml.exe CV tr=PKPD{p=AvgPer { lr=0.8 }} threads=- norm=No dout=/root/helix/work/workitem/e/TestOutput/PKPD/PKPD-CV-iris.txt data=/root/helix/work/correlation/test/data/iris.txt seed=1 xf=Term{col=Label}    Not adding a normalizer.    Training learner (0,0)    Training calibrator.    Training learner (1,0)    Training calibrator.    Training learner (1,1)    Training calibrator.    Training learner (2,0)    Training calibrator.    Training learner (2,1)    Training calibrator.    Training learner (2,2)    Training calibrator.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Training learner (0,0)    Training calibrator.    Training learner (1,0)    Training calibrator.    Training learner (1,1)    Training calibrator.    Training learner (2,0)    Training calibrator.    Training learner (2,1)    Training calibrator.    Training learner (2,2)    Training calibrator.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 21 | 0 | 0 | 1.0000    1 || 0 | 28 | 2 | 0.9333    2 || 0 | 0 | 28 | 1.0000    ||========================    Precision ||1.0000 |1.0000 |0.9333 |    Accuracy(micro-avg): 0.974684    Accuracy(macro-avg): 0.977778    Log-loss: 0.359335    Log-loss reduction: 0.669582      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 29 | 0 | 0 | 1.0000    1 || 0 | 18 | 2 | 0.9000    2 || 0 | 0 | 22 | 1.0000    ||========================    Precision ||1.0000 |1.0000 |0.9167 |    Accuracy(micro-avg): 0.971831    Accuracy(macro-avg): 0.966667    Log-loss: 0.277823    Log-loss reduction: 0.744095      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.973257 (0.0014)    Accuracy(macro-avg): 0.972222 (0.0056)    Log-loss: 0.318579 (0.0408)    Log-loss reduction: 0.706839 (0.0373)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.027      Comparing /root/helix/work/workitem/e/TestOutput/PKPD/PKPD-CV-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PKPD/PKPD-CV-iris-out.txt  Output matches baseline: 'PKPD/PKPD-CV-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/PKPD/PKPD-CV-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PKPD/PKPD-CV-iris-rp.txt  Output matches baseline: 'PKPD/PKPD-CV-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/PKPD/PKPD-CV-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/PKPD/PKPD-CV-iris.txt  Output matches baseline: 'PKPD/PKPD-CV-iris.txt'  Test MulticlassReductionTest: completed normally: passed  Microsoft.ML.RunTests.TestPredictors.WeightingClassificationNNPredictorsTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesHeterogeneousTest with memory usage 207,499,264.00 and max memory usage 213,299,200.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesHeterogeneousTest [PASS] Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesRandomSubSpaceSelectorTest  Output:  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{bp=svm bp=ap nm=20 tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{bp=svm bp=ap nm=20 tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 26 instances with missing features during training (over 1 iterations; 26 inst/iter)    Trainer 1 of 20 finished in 00:00:00.0011908    Beginning training model 2 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 150 instances with missing features during training (over 10 iterations; 15 inst/iter)    Trainer 2 of 20 finished in 00:00:00.0022908    Beginning training model 3 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 11 instances with missing features during training (over 1 iterations; 11 inst/iter)    Trainer 3 of 20 finished in 00:00:00.0002830    Beginning training model 4 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 120 instances with missing features during training (over 10 iterations; 12 inst/iter)    Trainer 4 of 20 finished in 00:00:00.0015951    Beginning training model 5 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 5 of 20 finished in 00:00:00.0002851    Beginning training model 6 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 150 instances with missing features during training (over 10 iterations; 15 inst/iter)    Trainer 6 of 20 finished in 00:00:00.0016398    Beginning training model 7 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 7 of 20 finished in 00:00:00.0003774    Beginning training model 8 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 180 instances with missing features during training (over 10 iterations; 18 inst/iter)    Trainer 8 of 20 finished in 00:00:00.0017763    Beginning training model 9 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 9 of 20 finished in 00:00:00.0002805    Beginning training model 10 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 180 instances with missing features during training (over 10 iterations; 18 inst/iter)    Trainer 10 of 20 finished in 00:00:00.0015934    Beginning training model 11 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 11 of 20 finished in 00:00:00.0002719    Beginning training model 12 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 130 instances with missing features during training (over 10 iterations; 13 inst/iter)    Trainer 12 of 20 finished in 00:00:00.0015722    Beginning training model 13 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 13 of 20 finished in 00:00:00.0002775    Beginning training model 14 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 170 instances with missing features during training (over 10 iterations; 17 inst/iter)    Trainer 14 of 20 finished in 00:00:00.0015022    Beginning training model 15 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 15 of 20 finished in 00:00:00.0002528    Beginning training model 16 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 120 instances with missing features during training (over 10 iterations; 12 inst/iter)    Trainer 16 of 20 finished in 00:00:00.0015622    Beginning training model 17 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 17 of 20 finished in 00:00:00.0002719    Beginning training model 18 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 190 instances with missing features during training (over 10 iterations; 19 inst/iter)    Trainer 18 of 20 finished in 00:00:00.0015503    Beginning training model 19 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 23 instances with missing features during training (over 1 iterations; 23 inst/iter)    Trainer 19 of 20 finished in 00:00:00.0002903    Beginning training model 20 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 180 instances with missing features during training (over 10 iterations; 18 inst/iter)    Trainer 20 of 20 finished in 00:00:00.0015374    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9625 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.112863    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.879162    AUC: 0.996249      OVERALL RESULTS    ---------------------------------------    AUC: 0.996249 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.962500 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981941 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.112863 (0.0000)    Log-loss reduction: 0.879162 (0.0000)    F1 Score: 0.964509 (0.0000)    AUPRC: 0.992435 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.044      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Hetero-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Hetero-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Hetero-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Hetero-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 9 | 435 | 0.9797    ||======================    Precision || 0.9625 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.975110    LOG LOSS/instance: 0.112863    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.879162    AUC: 0.996249      OVERALL RESULTS    ---------------------------------------    AUC: 0.996249 (0.0000)    Accuracy: 0.975110 (0.0000)    Positive precision: 0.962500 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981941 (0.0000)    Negative recall: 0.979730 (0.0000)    Log-loss: 0.112863 (0.0000)    Log-loss reduction: 0.879162 (0.0000)    F1 Score: 0.964509 (0.0000)    AUPRC: 0.992435 (0.0000)      ---------------------------------------    Physical memory usage(MB): 203    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.044      Suffix of length 34 compared against sequence of length 118  Test EnsemblesHeterogeneousTest: completed normally: passed  Test EnsemblesHeterogeneousTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesRandomSubSpaceSelectorTest with memory usage 216,014,848.00 and max memory usage 216,014,848.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesRandomSubSpaceSelectorTest [PASS] Starting test: Microsoft.ML.RunTests.TestPredictors.TestTreeEnsembleCombiner  Output:  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{nm=20 st=AllInstanceSelector{fs=RandomFeatureSelector} tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{nm=20 st=AllInstanceSelector{fs=RandomFeatureSelector} tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 1 of 20 finished in 00:00:00.0020647    Beginning training model 2 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 2 of 20 finished in 00:00:00.0007946    Beginning training model 3 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 3 of 20 finished in 00:00:00.0002267    Beginning training model 4 of 20    Trainer 4 of 20 finished in 00:00:00.0006276    Beginning training model 5 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 5 of 20 finished in 00:00:00.0006921    Beginning training model 6 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 6 of 20 finished in 00:00:00.0006144    Beginning training model 7 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 7 of 20 finished in 00:00:00.0006416    Beginning training model 8 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 8 of 20 finished in 00:00:00.0006310    Beginning training model 9 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 9 of 20 finished in 00:00:00.0005879    Beginning training model 10 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 10 of 20 finished in 00:00:00.0002364    Beginning training model 11 of 20    Trainer 11 of 20 finished in 00:00:00.0006258    Beginning training model 12 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 12 of 20 finished in 00:00:00.0002416    Beginning training model 13 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 13 of 20 finished in 00:00:00.0005906    Beginning training model 14 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 14 of 20 finished in 00:00:00.0005772    Beginning training model 15 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 15 of 20 finished in 00:00:00.0005762    Beginning training model 16 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 16 of 20 finished in 00:00:00.0006036    Beginning training model 17 of 20    Trainer 17 of 20 finished in 00:00:00.0005868    Beginning training model 18 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 18 of 20 finished in 00:00:00.0005795    Beginning training model 19 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 19 of 20 finished in 00:00:00.0005563    Beginning training model 20 of 20    Warning:  Skipped 16 instances with missing features during training (over 1 iterations; 16 inst/iter)    Trainer 20 of 20 finished in 00:00:00.0009802    Training calibrator.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 233 | 8 | 0.9668    negative || 12 | 446 | 0.9738    ||======================    Precision || 0.9510 | 0.9824 |    OVERALL 0/1 ACCURACY: 0.971388    LOG LOSS/instance: 0.130701    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.859358    AUC: 0.994931      OVERALL RESULTS    ---------------------------------------    AUC: 0.994931 (0.0000)    Accuracy: 0.971388 (0.0000)    Positive precision: 0.951020 (0.0000)    Positive recall: 0.966805 (0.0000)    Negative precision: 0.982379 (0.0000)    Negative recall: 0.973799 (0.0000)    Log-loss: 0.130701 (0.0000)    Log-loss reduction: 0.859358 (0.0000)    F1 Score: 0.958848 (0.0000)    AUPRC: 0.989467 (0.0000)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.097      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-RandomFeature-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-RandomFeature-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-RandomFeature-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-RandomFeature-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 233 | 8 | 0.9668    negative || 12 | 446 | 0.9738    ||======================    Precision || 0.9510 | 0.9824 |    OVERALL 0/1 ACCURACY: 0.971388    LOG LOSS/instance: 0.130701    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.859358    AUC: 0.994931      OVERALL RESULTS    ---------------------------------------    AUC: 0.994931 (0.0000)    Accuracy: 0.971388 (0.0000)    Positive precision: 0.951020 (0.0000)    Positive recall: 0.966805 (0.0000)    Negative precision: 0.982379 (0.0000)    Negative recall: 0.973799 (0.0000)    Log-loss: 0.130701 (0.0000)    Log-loss reduction: 0.859358 (0.0000)    F1 Score: 0.958848 (0.0000)    AUPRC: 0.989467 (0.0000)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:53 PM Time elapsed(s): 0.017      Suffix of length 33 compared against sequence of length 94  Test EnsemblesRandomSubSpaceSelectorTest: completed normally: passed  Test EnsemblesRandomSubSpaceSelectorTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.TestTreeEnsembleCombiner with memory usage 212,512,768.00 and max memory usage 216,801,280.00  Microsoft.ML.RunTests.TestPredictors.TestTreeEnsembleCombiner [PASS]  Output:  Test TestTreeEnsembleCombiner: aborted: passed  Microsoft.ML.RunTests.TestPredictors.BinaryClassifierLinearSvmTest [SKIP]  Need CoreTLC specific baseline update Starting test: Microsoft.ML.RunTests.TestPredictors.MulticlassNaiveBayes  Microsoft.ML.RunTests.TestPredictors.PoissonRegressorNonNegativeTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.MulticlassNaiveBayes with memory usage 212,668,416.00 and max memory usage 216,801,280.00 Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesVotingCombinerTest  Microsoft.ML.RunTests.TestPredictors.MulticlassNaiveBayes [PASS]  Output:  Running 'MultiClassNaiveBayes' on 'breast-cancer'  Running as: TrainTest tr=MultiClassNaiveBayes data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} cache- out={/root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=MultiClassNaiveBayes cache=- dout=/root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Not training a calibrator because it is not needed.      Confusion table    ||======================    PREDICTED || 0 | 1 | Recall    TRUTH ||======================    0 || 458 | 0 | 1.0000    1 || 241 | 0 | 0.0000    ||======================    Precision || 0.6552 | 0.0000 |    Accuracy(micro-avg): 0.655222    Accuracy(macro-avg): 0.500000    Log-loss: 34.538776    Log-loss reduction: -52.618809      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.655222 (0.0000)    Accuracy(macro-avg): 0.500000 (0.0000)    Log-loss: 34.538776 (0.0000)    Log-loss reduction: -52.618809 (0.0000)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:54 PM Time elapsed(s): 0.012      Comparing /root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer-out.txt  Output matches baseline: 'MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer.txt  Output matches baseline: 'MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-TrainTest-breast-cancer-model.zip seed=1      Confusion table    ||======================    PREDICTED || 0 | 1 | Recall    TRUTH ||======================    0 || 458 | 0 | 1.0000    1 || 241 | 0 | 0.0000    ||======================    Precision || 0.6552 | 0.0000 |    Accuracy(micro-avg): 0.655222    Accuracy(macro-avg): 0.500000    Log-loss: 34.538776    Log-loss reduction: -52.618809      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.655222 (0.0000)    Accuracy(macro-avg): 0.500000 (0.0000)    Log-loss: 34.538776 (0.0000)    Log-loss reduction: -52.618809 (0.0000)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:54 PM Time elapsed(s): 0.169      Suffix of length 26 compared against sequence of length 29  Running 'MultiClassNaiveBayes' on 'breast-cancer'  Running as: CV tr=MultiClassNaiveBayes data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} cache- dout={/root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer.txt} threads-  maml.exe CV tr=MultiClassNaiveBayes threads=- cache=- dout=/root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer.txt loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1    Not adding a normalizer.    Not training a calibrator because it is not needed.    Not adding a normalizer.    Not training a calibrator because it is not needed.      Confusion table    ||======================    PREDICTED || 0 | 1 | Recall    TRUTH ||======================    0 || 228 | 0 | 1.0000    1 || 134 | 0 | 0.0000    ||======================    Precision || 0.6298 | 0.0000 |    Accuracy(micro-avg): 0.629834    Accuracy(macro-avg): 0.500000    Log-loss: 34.538776    Log-loss reduction: -51.407404      Confusion table    ||======================    PREDICTED || 0 | 1 | Recall    TRUTH ||======================    0 || 230 | 0 | 1.0000    1 || 107 | 0 | 0.0000    ||======================    Precision || 0.6825 | 0.0000 |    Accuracy(micro-avg): 0.682493    Accuracy(macro-avg): 0.500000    Log-loss: 34.538776    Log-loss reduction: -54.264136      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.656163 (0.0263)    Accuracy(macro-avg): 0.500000 (0.0000)    Log-loss: 34.538776 (0.0000)    Log-loss reduction: -52.835770 (1.4284)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:54 PM Time elapsed(s): 0.013      Comparing /root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer-out.txt  Output matches baseline: 'MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer-rp.txt  Output matches baseline: 'MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer.txt  Output matches baseline: 'MultiClassNaiveBayes/MultiClassNaiveBayes-CV-breast-cancer.txt'  Test MulticlassNaiveBayes: completed normally: passed  Microsoft.ML.RunTests.TestPredictors.WeightingFastForestClassificationPredictorsTest [SKIP]  Need CoreTLC specific baseline update  Microsoft.ML.RunTests.TestPredictors.WeightingFastForestRegressionPredictorsTest [SKIP]  Need CoreTLC specific baseline update Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesVotingCombinerTest with memory usage 212,729,856.00 and max memory usage 216,801,280.00 Starting test: Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiStackCombinerTest  Microsoft.ML.RunTests.TestPredictors.EnsemblesVotingCombinerTest [PASS]  Output:  Running 'WeightedEnsemble' on 'breast-cancer'  Running as: TrainTest tr=WeightedEnsemble{nm=20 oc=Voting tp=-} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Voting-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Voting-TrainTest-breast-cancer.txt} loader=Text{col=Label:BL:0 col=Features:R4:1-9}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=WeightedEnsemble{nm=20 oc=Voting tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Voting-TrainTest-breast-cancer.txt loader=Text{col=Label:BL:0 col=Features:R4:1-9} data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Voting-TrainTest-breast-cancer-model.zip seed=1    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 20 learners for the batch 1    Beginning training model 1 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 26 instances with missing features during training (over 1 iterations; 26 inst/iter)    Trainer 1 of 20 finished in 00:00:00.0007643    Beginning training model 2 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 2 of 20 finished in 00:00:00.0009123    Beginning training model 3 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 11 instances with missing features during training (over 1 iterations; 11 inst/iter)    Trainer 3 of 20 finished in 00:00:00.0002886    Beginning training model 4 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 4 of 20 finished in 00:00:00.0002854    Beginning training model 5 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 5 of 20 finished in 00:00:00.0002923    Beginning training model 6 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 6 of 20 finished in 00:00:00.0002718    Beginning training model 7 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 7 of 20 finished in 00:00:00.0002562    Beginning training model 8 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 8 of 20 finished in 00:00:00.0003012    Beginning training model 9 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 15 instances with missing features during training (over 1 iterations; 15 inst/iter)    Trainer 9 of 20 finished in 00:00:00.0002716    Beginning training model 10 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 10 of 20 finished in 00:00:00.0002620    Beginning training model 11 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 11 of 20 finished in 00:00:00.0002538    Beginning training model 12 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 13 instances with missing features during training (over 1 iterations; 13 inst/iter)    Trainer 12 of 20 finished in 00:00:00.0003030    Beginning training model 13 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 14 instances with missing features during training (over 1 iterations; 14 inst/iter)    Trainer 13 of 20 finished in 00:00:00.0002608    Beginning training model 14 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 17 instances with missing features during training (over 1 iterations; 17 inst/iter)    Trainer 14 of 20 finished in 00:00:00.0002754    Beginning training model 15 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 24 instances with missing features during training (over 1 iterations; 24 inst/iter)    Trainer 15 of 20 finished in 00:00:00.0002851    Beginning training model 16 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 16 of 20 finished in 00:00:00.0002722    Beginning training model 17 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 12 instances with missing features during training (over 1 iterations; 12 inst/iter)    Trainer 17 of 20 finished in 00:00:00.0002583    Beginning training model 18 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 19 instances with missing features during training (over 1 iterations; 19 inst/iter)    Trainer 18 of 20 finished in 00:00:00.0003441    Beginning training model 19 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 23 instances with missing features during training (over 1 iterations; 23 inst/iter)    Trainer 19 of 20 finished in 00:00:00.0002573    Beginning training model 20 of 20    Warning:  Training data does not support shuffling, so ignoring request to shuffle    Warning:  Skipped 18 instances with missing features during training (over 1 iterations; 18 inst/iter)    Trainer 20 of 20 finished in 00:00:00.0002692    Training calibrator.    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9585 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.129466    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.861385    AUC: 0.992339      OVERALL RESULTS    ---------------------------------------    AUC: 0.992339 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.958506 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981900 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.129466 (0.0000)    Log-loss reduction: 0.861385 (0.0000)    F1 Score: 0.962500 (0.0000)    AUPRC: 0.963675 (0.0000)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:54 PM Time elapsed(s): 0.03      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Voting-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Voting-TrainTest-breast-cancer-out.txt  Output matches baseline: 'WeightedEnsemble/WE-Voting-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Voting-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Voting-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'WeightedEnsemble/WE-Voting-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Voting-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsemble/linux-arm64/WE-Voting-TrainTest-breast-cancer.txt  Output matches baseline: 'WeightedEnsemble/WE-Voting-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Voting-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsemble/WE-Voting-TrainTest-breast-cancer-model.zip seed=1    Warning:  The predictor produced non-finite prediction values on 16 instances during testing. Possible causes: abnormal data or the predictor is numerically unstable.    TEST POSITIVE RATIO: 0.3499 (239.0/(239.0+444.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 231 | 8 | 0.9665    negative || 10 | 434 | 0.9775    ||======================    Precision || 0.9585 | 0.9819 |    OVERALL 0/1 ACCURACY: 0.973646    LOG LOSS/instance: 0.129466    Test-set entropy (prior Log-Loss/instance): 0.934003    LOG-LOSS REDUCTION (RIG): 0.861385    AUC: 0.992339      OVERALL RESULTS    ---------------------------------------    AUC: 0.992339 (0.0000)    Accuracy: 0.973646 (0.0000)    Positive precision: 0.958506 (0.0000)    Positive recall: 0.966527 (0.0000)    Negative precision: 0.981900 (0.0000)    Negative recall: 0.977477 (0.0000)    Log-loss: 0.129466 (0.0000)    Log-loss reduction: 0.861385 (0.0000)    F1 Score: 0.962500 (0.0000)    AUPRC: 0.963675 (0.0000)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:54 PM Time elapsed(s): 0.013      Suffix of length 34 compared against sequence of length 118  Test EnsemblesVotingCombinerTest: completed normally: passed  Test EnsemblesVotingCombinerTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiStackCombinerTest with memory usage 215,441,408.00 and max memory usage 216,801,280.00  Microsoft.ML.RunTests.TestPredictors.EnsemblesMultiStackCombinerTest [PASS]  Output:  Running 'WeightedEnsembleMulticlass' on 'iris'  Running as: TrainTest tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=5 oc=MultiStacking{bp=mlr{t-}} tp=-} data=/root/helix/work/correlation/test/data/iris.txt seed=1 test=/root/helix/work/correlation/test/data/iris.txt xf=Term{col=Label} out={/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris-model.zip} dout={/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/iris.txt tr=WeightedEnsembleMulticlass{bp=mlr{t-} nm=5 oc=MultiStacking{bp=mlr{t-}} tp=-} dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt out=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris-model.zip seed=1 xf=Term{col=Label}    Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.    Training 5 learners for the batch 1    Beginning training model 1 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 10 of 15 weights.    Trainer 1 of 5 finished in 00:00:00.0079607    Beginning training model 2 of 5   Starting test: Microsoft.ML.RunTests.TestPredictors.GamBinaryClassificationTest  Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 12 of 15 weights.    Trainer 2 of 5 finished in 00:00:00.0070724    Beginning training model 3 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 3 of 5 finished in 00:00:00.0062069    Beginning training model 4 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 11 of 15 weights.    Trainer 4 of 5 finished in 00:00:00.0263394    Beginning training model 5 of 5    Beginning optimization    num vars: 15    improvement criterion: Mean Improvement    L1 regularization selected 13 of 15 weights.    Trainer 5 of 5 finished in 00:00:00.0081736    The number of instances used for stacking trainer is 43    Warning:  The trainer specified for stacking wants normalization, but we do not currently allow this.    Beginning optimization    num vars: 48    improvement criterion: Mean Improvement    L1 regularization selected 26 of 48 weights.    Not training a calibrator because it is not needed.      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 35 | 15 | 0.7000    2 || 0 | 0 | 50 | 1.0000    ||========================    Precision ||1.0000 |1.0000 |0.7692 |    Accuracy(micro-avg): 0.900000    Accuracy(macro-avg): 0.900000    Log-loss: 0.430565    Log-loss reduction: 0.608083      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.900000 (0.0000)    Accuracy(macro-avg): 0.900000 (0.0000)    Log-loss: 0.430565 (0.0000)    Log-loss reduction: 0.608083 (0.0000)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:54 PM Time elapsed(s): 0.077      Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Stacking-TrainTest-iris-out.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Stacking-TrainTest-iris-rp.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris.txt and /root/helix/work/correlation/test/BaselineOutput/Common/WeightedEnsembleMulticlass/linux-arm64/WE-Stacking-TrainTest-iris.txt  Output matches baseline: 'WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris.txt data=/root/helix/work/correlation/test/data/iris.txt in=/root/helix/work/workitem/e/TestOutput/WeightedEnsembleMulticlass/WE-Stacking-TrainTest-iris-model.zip seed=1      Confusion table    ||========================    PREDICTED || 0 | 1 | 2 | Recall    TRUTH ||========================    0 || 50 | 0 | 0 | 1.0000    1 || 0 | 35 | 15 | 0.7000    2 || 0 | 0 | 50 | 1.0000    ||========================    Precision ||1.0000 |1.0000 |0.7692 |    Accuracy(micro-avg): 0.900000    Accuracy(macro-avg): 0.900000    Log-loss: 0.430565    Log-loss reduction: 0.608083      OVERALL RESULTS    ---------------------------------------    Accuracy(micro-avg): 0.900000 (0.0000)    Accuracy(macro-avg): 0.900000 (0.0000)    Log-loss: 0.430565 (0.0000)    Log-loss reduction: 0.608083 (0.0000)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:55 PM Time elapsed(s): 0.009      Suffix of length 27 compared against sequence of length 67  Test EnsemblesMultiStackCombinerTest: completed normally: passed  Test EnsemblesMultiStackCombinerTest is using linux-arm64 configuration specific baselines. Finished test: Microsoft.ML.RunTests.TestPredictors.GamBinaryClassificationTest with memory usage 220,372,992.00 and max memory usage 220,372,992.00  Microsoft.ML.RunTests.TestPredictors.GamBinaryClassificationTest [PASS]  Output:  Running 'BinaryClassificationGamTrainer' on 'breast-cancer'  Running as: TrainTest tr=BinaryClassificationGamTrainer data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=BinaryClassificationGamTrainer dout=/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise    Warning:  Skipped 16 instances with missing features during training    Processed 683 instances    Binning and forming Feature objects    Starting to train ...    Training calibrator.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 9 | 0.9627    negative || 12 | 446 | 0.9738    ||======================    Precision || 0.9508 | 0.9802 |    OVERALL 0/1 ACCURACY: 0.969957    LOG LOSS/instance: 0.113509    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.877858    AUC: 0.994972      OVERALL RESULTS    ---------------------------------------    AUC: 0.994972 (0.0000)    Accuracy: 0.969957 (0.0000)    Positive precision: 0.950820 (0.0000)    Positive recall: 0.962656 (0.0000)    Negative precision: 0.980220 (0.0000)    Negative recall: 0.973799 (0.0000)    Log-loss: 0.113509 (0.0000)    Log-loss reduction: 0.877858 (0.0000)    F1 Score: 0.956701 (0.0000)    AUPRC: 0.989577 (0.0000)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:55 PM Time elapsed(s): 0.479      Comparing /root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer-out.txt  Output matches baseline: 'BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer.txt  Output matches baseline: 'BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainer-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 9 | 0.9627    negative || 12 | 446 | 0.9738    ||======================    Precision || 0.9508 | 0.9802 |    OVERALL 0/1 ACCURACY: 0.969957    LOG LOSS/instance: 0.113509    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.877858    AUC: 0.994972      OVERALL RESULTS    ---------------------------------------    AUC: 0.994972 (0.0000)    Accuracy: 0.969957 (0.0000)    Positive precision: 0.950820 (0.0000)    Positive recall: 0.962656 (0.0000)    Negative precision: 0.980220 (0.0000)    Negative recall: 0.973799 (0.0000)    Log-loss: 0.113509 (0.0000)    Log-loss reduction: 0.877858 (0.0000)    F1 Score: 0.956701 (0.0000)    AUPRC: 0.989577 (0.0000)      ---------------------------------------    Physical memory usage(MB): 206    Virtual memory usage(MB): 266875    09/21/2026 13:02:55 PM Time elapsed(s): 0.007      Suffix of length 33 compared against sequence of length 42  Running 'BinaryClassificationGamTrainer' on 'breast-cancer'  Running as: TrainTest tr=BinaryClassificationGamTrainer{dt+} data=/root/helix/work/correlation/test/data/breast-cancer.txt seed=1 test=/root/helix/work/correlation/test/data/breast-cancer.txt out={/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer-model.zip} dout={/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer.txt}  maml.exe TrainTest test=/root/helix/work/correlation/test/data/breast-cancer.txt tr=BinaryClassificationGamTrainer{dt+} dout=/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt out=/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer-model.zip seed=1    Not adding a normalizer.    Making per-feature arrays    Changing data from row-wise to column-wise on disk    Warning:  16 of 699 examples will be skipped due to missing feature values    Processed 683 instances    Binning and forming Feature objects    Starting to train ...    Training calibrator.    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 9 | 0.9627    negative || 12 | 446 | 0.9738    ||======================    Precision || 0.9508 | 0.9802 |    OVERALL 0/1 ACCURACY: 0.969957    LOG LOSS/instance: 0.113509    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.877858    AUC: 0.994972      OVERALL RESULTS    ---------------------------------------    AUC: 0.994972 (0.0000)    Accuracy: 0.969957 (0.0000)    Positive precision: 0.950820 (0.0000)    Positive recall: 0.962656 (0.0000)    Negative precision: 0.980220 (0.0000)    Negative recall: 0.973799 (0.0000)    Log-loss: 0.113509 (0.0000)    Log-loss reduction: 0.877858 (0.0000)    F1 Score: 0.956701 (0.0000)    AUPRC: 0.989577 (0.0000)      ---------------------------------------    Physical memory usage(MB): 210    Virtual memory usage(MB): 266875    09/21/2026 13:02:56 PM Time elapsed(s): 0.415      Comparing /root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer-out.txt and /root/helix/work/correlation/test/BaselineOutput/Common/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer-out.txt  Output matches baseline: 'BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer-out.txt'  Comparing /root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer-rp.txt and /root/helix/work/correlation/test/BaselineOutput/Common/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer-rp.txt  Output matches baseline: 'BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer-rp.txt'  Comparing /root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer.txt and /root/helix/work/correlation/test/BaselineOutput/Common/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer.txt  Output matches baseline: 'BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer.txt'  maml.exe Test dout=/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer.txt data=/root/helix/work/correlation/test/data/breast-cancer.txt in=/root/helix/work/workitem/e/TestOutput/BinaryClassificationGamTrainer/BinaryClassificationGamTrainerDiskTranspose-TrainTest-breast-cancer-model.zip seed=1    TEST POSITIVE RATIO: 0.3448 (241.0/(241.0+458.0))    Confusion table    ||======================    PREDICTED || positive | negative | Recall    TRUTH ||======================    positive || 232 | 9 | 0.9627    negative || 12 | 446 | 0.9738    ||======================    Precision || 0.9508 | 0.9802 |    OVERALL 0/1 ACCURACY: 0.969957    LOG LOSS/instance: 0.113509    Test-set entropy (prior Log-Loss/instance): 0.929318    LOG-LOSS REDUCTION (RIG): 0.877858    AUC: 0.994972      OVERALL RESULTS    ---------------------------------------    AUC: 0.994972 (0.0000)    Accuracy: 0.969957 (0.0000)    Positive precision: 0.950820 (0.0000)    Positive recall: 0.962656 (0.0000)    Negative precision: 0.980220 (0.0000)    Negative recall: 0.973799 (0.0000)    Log-loss: 0.113509 (0.0000)    Log-loss reduction: 0.877858 (0.0000)    F1 Score: 0.956701 (0.0000)    AUPRC: 0.989577 (0.0000)      ---------------------------------------    Physical memory usage(MB): 210    Virtual memory usage(MB): 266875    09/21/2026 13:02:56 PM Time elapsed(s): 0.007      Suffix of length 33 compared against sequence of length 42  Test GamBinaryClassificationTest: completed normally: passed  Microsoft.ML.RunTests.TestPredictors.RegressorOlsTestOne [SKIP]  This test requires a native library MklImports that wasn't found.  Microsoft.ML.RunTests.TestPredictors.FastTreeRankingTest [SKIP]  Need CoreTLC specific baseline update  Finished: Microsoft.ML.Predictor.Tests === TEST EXECUTION SUMMARY ===  Microsoft.ML.Predictor.Tests Total: 115, Errors: 0, Failed: 7, Skipped: 57, Time: 22.945s /root/helix/work/workitem/e ----- end Mon Sep 21 01:02:56 PM UTC 2026 ----- exit code 1 ---------------------------------------------------------- + export _commandExitCode=0 + python /root/helix/work/correlation/reporter/run.py https://dev.azure.com/dnceng-public/ public 44343250 eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsIng1dCI6ImRndlNEdks4QTVLeUt5cHB3MWRBd1RYRDNDQSIsImtpZCI6ImRndlNEdks4QTVLeUt5cHB3MWRBd1RYRDNDQSJ9.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.V81PrlZzlW6WxYphDOdRyYOJWWhnWeYkz_WSwQK8dxwkMhtnJx59NQRuKzmdW9bq7RE27J0cZB5lNLkV-hgNiN8r3vTF6Qb7nFZm-90i0rUzI0txi3jE-apy14cTAgf3Sw2AqkvLpQhX-kuXVolAz9MlLv8dwFqO_hzqksdcNZMZd48u2YhIfDlr_6BY8TmOASASWyWvs5jqTCTsvkUyxKwVPK-BFnimR30PQ4QvlCgTcfXpSyxb_jqt_wOARMU4s_str_pi2emgyRm6FSe2hPe-2UoWAC-D7bqTwTE55LjesVvV5TaMkD82JMDFLbFz3UjkU2UVIJyyY1oS9uZ06A /home/helixbot/.vsts-env/lib/python3.10/site-packages/azure/__init__.py:5: 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. import pkg_resources 2026-09-21T13:02:57.078Z INFO run.py managed_identity(151) __init__ ManagedIdentityCredential will use IMDS with client_id: 3423231b-6b9e-4177-8817-76276b647404 2026-09-21T13:02:57.078Z INFO run.py azure_utils(32) get_credential_and_access_token VMSSManagedIdentity VmssMIClientIdForUpload Auth type will be used 2026-09-21T13:02:57.078Z INFO run.py _universal(535) on_request Request URL: 'http://169.254.169.254/metadata/identity/oauth2/token?api-version=2018-02-01&resource=REDACTED&client_id=REDACTED' Request method: 'GET' Request headers: 'Metadata': 'REDACTED' 'x-client-SKU': 'REDACTED' 'x-client-Ver': 'REDACTED' 'x-ms-client-request-id': 'f9a9f01a-8870-4e2f-9439-8334b4fb9890' 'User-Agent': 'azsdk-python-identity/1.25.3 Python/3.10.12 (Linux-6.8.0-1063-azure-aarch64-with-glibc2.35)' No body was attached to the request 2026-09-21T13:02:57.089Z INFO run.py _universal(581) on_response Response status: 200 Response headers: 'Content-Type': 'application/json; charset=utf-8' 'Server': 'IMDS/150.870.65.2128' 'x-ms-request-id': 'f9a9f01a-8870-4e2f-9439-8334b4fb9890' 'Date': 'Mon, 21 Sep 2026 13:02:56 GMT' 'Content-Length': '2537' 2026-09-21T13:02:57.089Z INFO run.py msal_managed_identity_client(165) _get_token_base ImdsCredential.get_token succeeded 2026-09-21T13:02:57.089Z INFO run.py decorators(24) wrapper ManagedIdentityCredential.get_token succeeded 2026-09-21T13:02:57.090Z INFO run.py azure_utils(64) get_credential_and_access_token Credentials are valid 2026-09-21T13:02:57.091Z INFO run.py msal_managed_identity_client(165) _get_token_base ImdsCredential.get_token_info succeeded 2026-09-21T13:02:57.091Z INFO run.py decorators(24) wrapper ManagedIdentityCredential.get_token_info succeeded 2026-09-21T13:02:57.166Z INFO run.py run(67) main Beginning reading of test results. 2026-09-21T13:02:57.166Z INFO run.py __init__(49) read_results Searching '/root/helix/work/workitem/e' for test results files 2026-09-21T13:02:57.175Z INFO run.py __init__(55) read_results Found results file /root/helix/work/workitem/e/testResults.xml with format xunit 2026-09-21T13:02:57.182Z INFO run.py __init__(49) read_results Searching '/root/helix/work/workitem/uploads' for test results files 2026-09-21T13:02:57.182Z INFO run.py packing_test_reporter(30) report_results Packing 115 test reports to '/root/helix/work/workitem/e/__test_report.json' 2026-09-21T13:02:57.183Z INFO run.py packing_test_reporter(33) report_results Packed 242883 bytes 2026-09-21T13:02:57.183Z INFO run.py _helix_compat(255) report_results Writing 0 test results to '/root/helix/work/workitem/e/__test_report_v2.json' (JSON v1) 2026-09-21T13:02:57.183Z INFO run.py _helix_compat(261) report_results Wrote 2628 bytes to '/root/helix/work/workitem/e/__test_report_v2.json' + exit 0 + _commandExitCode=0 + chmod -R 777 /datadisks/disk1/dumps + exit 0 [END EXECUTION] Exit Code:0