MetaTrainingStepResult<T>
Models & Types · AiDotNet.Models.Results
Results from a single meta-training step (one outer loop update).
For Beginners
Think of this as the “score” for one training iteration.
Each meta-training iteration:
- Samples a batch of tasks (e.g., 4 tasks)
- Adapts to each task (inner loop)
- Updates meta-parameters based on adaptation results (outer loop)
- Returns these metrics to show how well that update performed
You’ll get one of these for each iteration during training, allowing you to:
- Monitor training progress in real-time
- Log metrics to TensorBoard or similar tools
- Implement early stopping or learning rate schedules
- Debug training issues as they occur
How It Works
This class represents metrics from one iteration of meta-training, tracking the performance of a single outer loop update across a batch of tasks. It’s a lightweight snapshot designed for real-time monitoring during training.
Constructors
| Constructor | Summary |
|---|---|
MetaTrainingStepResult(T metaLoss, T taskLoss, T accuracy, int numTasks, int iteration, double timeMs, Dictionary<string, T> additionalMetrics) |
Initializes a new instance with metrics from one meta-training step. |
Properties
| Property | Summary |
|---|---|
Dictionary<string, T> AdditionalMetrics { get; } |
Gets algorithm-specific metrics for this training step. |
T Accuracy { get; } |
Gets the average accuracy across tasks in this step. |
T MetaLoss { get; } |
Gets the meta-loss for this training step. |
T TaskLoss { get; } |
Gets the average task-specific loss after adaptation. |
double TimeMs { get; } |
Gets the time taken for this meta-training step in milliseconds. |
int Iteration { get; } |
Gets the iteration number for this training step. |
int NumTasks { get; } |
Gets the number of tasks processed in this meta-training step. |
Methods
| Method | Summary |
|---|---|
string ToString() |
Returns a concise string representation for logging. |