Data classification - Metadata KeyValues does not exist

**System Information (please complete the following information):**
- Model Builder Version: 4.0.2
- Visual Studio Version: 2022 Community - 17.13.1

**Describe the bug**
- On which step of the process did you run into an issue: Training the model with the CSV file
- Clear description of the problem: I have a CSV file with 2 headers: Label, Prediction
When i add this file as a data source and select the prediction column as the one to predict i can click next step without any issues.
However, after i click Train on the next screen i get a Model Builder error with the message: Metadata KeyValues does not exist
at Microsoft.ML.Runtime.Contracts.Check(IExceptionContext ctx, Boolean f, String msg)
at Microsoft.ML.Transforms.KeyToValueMappingTransformer.Mapper.ComputeKvMaps(DataViewSchema schema, DataViewType[]& types, KeyToValueMap[]& kvMaps)
at Microsoft.ML.Transforms.KeyToValueMappingTransformer.Mapper..ctor(KeyToValueMappingTransformer parent, DataViewSchema inputSchema)
at Microsoft.ML.Transforms.KeyToValueMappingTransformer.MakeRowMapper(DataViewSchema inputSchema)
at Microsoft.ML.Data.RowToRowTransformerBase.GetOutputSchema(DataViewSchema inputSchema)
at Microsoft.ML.Data.TrivialEstimator`1.Fit(IDataView input)
at Microsoft.ML.Data.EstimatorChain`1.Fit(IDataView input)
at Microsoft.ML.AutoML.SweepablePipelineRunner.Run(TrialSettings settings)
at Microsoft.ML.AutoML.SweepablePipelineRunner.RunAsync(TrialSettings settings, CancellationToken ct)
at Microsoft.ML.AutoML.AutoMLExperiment.RunAsync(CancellationToken ct)
at Microsoft.ML.ModelBuilder.AutoMLService.Experiments.MultiClassificationExperiment.ExecuteAsync(IDataView trainData, IDataView validateData, CancellationToken ct) in /_/src/Microsoft.ML.ModelBuilder.AutoMLService/Experiments/MultiClassificationExperiment.cs:line 140
at Microsoft.ML.ModelBuilder.AutoMLEngine.StartTrainingAsync(ITrainingConfiguration config, PathConfiguration pathConfig, CancellationToken userCancellationToken) in /_/src/Microsoft.ML.ModelBuilder.AutoMLService/AutoMLEngineService/AutoMLEngine.cs:line 178

**To Reproduce**
Honestly not sure if you can reproduce this, im only getting it with my data but ill put my steps anyway.
Steps to reproduce the behavior:
1. Create a model and input the CSV file as a data source under the Data Classifiication scenario
2. Select the prediction column to predict
3. Start training the model
4. See error

**Expected behavior**
For the model training to finish

**Screenshots**
[Picture of the model builder error](https://cdn.itsgamertime.xyz/pictures2/5S2rNU.png)
[VS Code output](https://cdn.itsgamertime.xyz/pictures2/IW6WTc.png)
[Line 68-70 where the output said bad value](https://cdn.itsgamertime.xyz/pictures2/smzcSa.png)

**Additional context**
[Untitled-1.txt](https://github.com/user-attachments/files/19000486/Untitled-1.txt)
Attached log file

Beginnen Sie mit dem beigefügten Log und dem Stacktrace. Untersuchen Sie dann MultiClassificationExperiment.cs in Zeile 140 und AutoEngine.cs in Zeile 178, um die Trainingseingabe bis in AutoML zu verfolgen. Reproduzieren Sie den Data Classification-Workflow mit der gemeldeten zweispaltigen CSV und ermitteln Sie, warum das Training KeyToValueMappingTransformer ohne die erwarteten Metadaten erreicht; als abgeschlossen gilt die Aufgabe, wenn das Training erfolgreich abgeschlossen wird.

Vom Indexierungsmodell aus dem Issue-Text verfasst.