Error afrer Train NER -

**System Information:**
- Model Builder Version: [v17.18.0]
- Visual Studio Version: 2022

**Describe the bug**
- After completed the 10 epoch raise an error : Invalid call to 'GetValue'

**To Reproduce**
Steps to reproduce the behavior:
1. Add Machine Learning Model to the project (.net8 Console)
2. Select Scenario -> Named Entity Recognition
3. Select the Environment -> Local CPU
4. Select the Entities Key File
5. Select The Data Train file
6. Start the Training

**Expected behavior**
Finish Succesfull the training

**Log Output**
```
Named entity recognition
runtime already exist, skip install
Use cross validation with fold: 5
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 0
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 0
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 1
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 1
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 2
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 2
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 3
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 3
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 4
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 4
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 5
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 5
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 6
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 6
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 7
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 7
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 8
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 8
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 9
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 9
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 0
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 0
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 1
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 1
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 2
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 2
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 3
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 3
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 4
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 4
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 5
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 5
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 6
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 6
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 7
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 7
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 8
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 8
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Starting epoch 9
[Source=AutoMLExperiment-ChildContext, Kind=Trace] [Source=TorchSharpBaseTrainer; TrainModel, Kind=Trace] Finished epoch 9
```
**Behaviour**
Train start, finish all epochs without error, when finished the last epoch raise the error.

**Error Output**
```
Invalid call to 'GetValue'
at Microsoft.ML.DataViewSchema.Annotations.GetValue[TValue](String kind, TValue& value)
at Microsoft.ML.Data.SchemaAnnotationsExtensions.GetKeyValues[TValue](Column column, VBuffer`1& keyValues)
at Microsoft.ML.TorchSharp.NasBert.NerTrainer.Trainer.GetRowCountAndSetLabelCount(IDataView input)
at Microsoft.ML.TorchSharp.TorchSharpBaseTrainer`2.TrainerBase..ctor(TorchSharpBaseTrainer`2 parent, IChannel ch, IDataView input, String modelUrl)
at Microsoft.ML.TorchSharp.NasBert.NasBertTrainer`2.NasBertTrainerBase..ctor(TorchSharpBaseTrainer`2 parent, IChannel ch, IDataView input, String modelUrl)
at Microsoft.ML.TorchSharp.NasBert.NerTrainer.Trainer..ctor(TorchSharpBaseTrainer`2 parent, IChannel ch, IDataView input)
at Microsoft.ML.TorchSharp.NasBert.NerTrainer.CreateTrainer(TorchSharpBaseTrainer`2 parent, IChannel ch, IDataView input)
at Microsoft.ML.TorchSharp.TorchSharpBaseTrainer`2.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.NamedEntityRecognitionExperiment.ExecuteAsync(IDataView trainData, IDataView validateData, CancellationToken ct) in /_/src/Microsoft.ML.ModelBuilder.AutoMLService/Experiments/NamedEntityRecognitionExperiment.cs:line 133
at Microsoft.ML.ModelBuilder.AutoMLEngine.StartTrainingAsync(ITrainingConfiguration config, PathConfiguration pathConfig, CancellationToken userCancellationToken) in /_/src/Microsoft.ML.ModelBuilder.AutoMLService/AutoMLEngineService/AutoMLEngine.cs:line 178
```

**Data Files**

**Label Key File Content:**
S-PER
B-LOC
I-LOC
E-LOC
S-ORG
O

**Data Set Content**
Marco ha incontrato Anna al Duomo di Milano . S-PER O O S-PER O B-LOC I-LOC E-LOC O
La Ferrari presenterà la nuova auto . O S-ORG O O O O O

**Data Files To Download**

[Labels.txt](https://github.com/user-attachments/files/18273209/Labels.txt)
[ner_data.txt](https://github.com/user-attachments/files/18273215/ner_data.txt)

Reproduziere den Trainingsfehler mit Labels.txt und ner_data.txt und untersuche dann NamedEntityRecognitionExperiment.cs in Zeile 133 sowie den Stack-Eintrag NerTrainer.GetRowCountAndSetLabelCount. Vergleiche das Eingabeschema und die Label-Annotationen an dem Punkt, an dem der abschließende Training-Versuch beginnt; fertig ist die Aufgabe, wenn die bereitgestellten NER-Daten das Training ohne den Fehler Invalid call to 'GetValue' abschließen.

Vom Indexierungsmodell aus dem Issue-Text verfasst.