Training Loss Curve Calculator

Plot training, validation, and test losses, compare experiments, detect overfitting, identify convergence, simulate early stopping, smooth curves, and export complete diagnostic reports with confidence.

Loss data and settings

Use columns: epoch, training, validation, test, and run. Headers are optional.

Curve visibility and style


Smoothing and analysis


Early stopping


Chart and axes


Annotations and references

Formula used

Absolute reduction: initial loss minus final loss. It shows total improvement. Larger positive values indicate stronger reduction.

Percentage reduction: absolute reduction divided by initial loss. The result is multiplied by one hundred. It compares progress across different scales.

Generalisation gap: validation loss minus training loss. Positive gaps indicate weaker unseen-data performance. Large growing gaps can indicate overfitting.

Recent slope: linear-regression slope across recent epochs. Values near zero indicate convergence. Positive slopes indicate increasing monitored loss.

Early stopping: stop after patience epochs without minimum improvement. The best monitored checkpoint is recorded. Restoring it can improve generalisation.

How to use

  1. Paste loss data or upload a CSV file.
  2. Select visible curves, smoothing, and monitoring options.
  3. Configure convergence and early-stopping thresholds.
  4. Adjust chart labels, scales, and reference lines.
  5. Select Analyze loss curves to calculate results.
  6. Review diagnostics, rankings, tables, and export options.

Example data patterns

PatternTypical interpretation
Healthy convergenceTraining and validation losses decline together.
OverfittingTraining loss falls while validation loss rises.
UnderfittingBoth losses remain high and improve slowly.
OscillationLoss repeatedly rises and falls across epochs.
Exploding lossLoss grows rapidly instead of decreasing.
PlateauLoss changes become negligible for many epochs.
Early stoppingValidation improvement stops before training ends.
Model comparisonSeveral runs are ranked by validation loss.

Frequently asked questions

What is a training loss curve?

A training loss curve shows how model error changes during training. Epochs usually appear horizontally. Lower loss generally indicates improved fitting.

Why compare training and validation loss?

The comparison reveals generalisation behavior. Falling training loss with rising validation loss may indicate overfitting. Similar downward curves usually indicate healthier learning.

Can loss values be negative?

Some custom objectives can produce negative values. Many common losses remain nonnegative. The calculator warns instead of rejecting every negative value.

What does a plateau mean?

A plateau means recent loss improvement is very small. Training may have converged. Learning-rate changes or early stopping may help.

How is the best epoch selected?

The calculator uses the minimum monitored loss. Validation loss is preferred when available. Training loss becomes the fallback metric.

What is early-stopping patience?

Patience counts tolerated epochs without meaningful improvement. Training stops when that count is exceeded. The best checkpoint remains available for restoration.

Does smoothing change the original data?

Smoothing only affects displayed or analysed series when selected. Raw values remain preserved. Exports can include both raw and smoothed values.

What indicates unstable optimisation?

Large repeated rises and falls suggest instability. Excessive learning rates often cause this pattern. Noisy batches can also produce oscillations.

Can I compare multiple experiments?

Yes. Add a run column to your data. Every run receives separate curves, statistics, rankings, and diagnostic summaries.

Which CSV columns are supported?

Use epoch, training, validation, test, and run columns. Column names are case insensitive. Missing optional loss columns are accepted.

How should logarithmic loss charts be used?

Logarithmic scaling helps compare large proportional changes. Every plotted loss must be positive. Zero or negative values cannot appear on logarithmic axes.

Related Calculators

Validation CurveValidation Loss CurveAccuracy CurveError Rate CurveBias-Variance CurveCross-Validation Score PlotModel Comparison Bar ChartMetric Radar ChartHyperparameter Performance HeatmapRuntime-versus-Accuracy Plot

Important Note: All the Calculators listed in this site are for educational purpose only and we do not guarentee the accuracy of results. Please do consult with other sources as well.