Learning-Rate Curve Calculator

Explore learning-rate schedules, compare decay strategies, run range tests, inspect training behavior, and export clear charts with practical optimizer recommendations for every model workflow.

Calculated Results

Results update after calculation or preset loading.

Schedule mode

Recommendations and diagnostics

Generated data preview

Calculator mode

Schedule inputs

Learning-rate range-test inputs

Custom data and CSV import

Use columns: x, learning_rate, optional loss. Commas, tabs, spaces, semicolons, and new lines are accepted.

XLearning rateLossAction

Schedule comparison

Enable up to three additional schedules. Each curve can use its own method, label, and key parameters.

Chart customization

Export and utilities

Formula used

Exponential decay: ηₜ = η₀e−kt

Step decay: ηₜ = η₀γ⌊t/s⌋

Inverse-time decay: ηₜ = η₀ / (1 + kt)

Polynomial decay: ηₜ = (η₀ − ηmin)(1 − t/T)p + ηmin

Cosine annealing: ηₜ = ηmin + 0.5(ηmax − ηmin)(1 + cos(πt/T))

Linear warmup: ηₜ = ηmax(t/Tw)

How to use

  1. Select schedule mode or range-test mode.
  2. Choose a method and enter valid parameters.
  3. Optionally import custom learning-rate or loss data.
  4. Enable comparison schedules and customize the chart.
  5. Press Calculate, then inspect metrics and recommendations.
  6. Export the data, image, JSON, CSV, or printable PDF.

Worked example

A warmup-cosine schedule starts at 0.00001 and rises toward 0.003 during five epochs. It then decays smoothly toward 0.00001 across the remaining training period. This can stabilize early updates while preserving useful progress later.

EpochLearning rateInterpretation
00.00001Warmup begins
50.00300Peak rate reached
50About 0.00150Cosine decay continues
1000.00001Training finishes gently

Learning-rate curve guidance

Why schedules matter

Large rates can speed early learning but may cause unstable updates. Smaller rates support fine adjustments near convergence. A schedule balances exploration, speed, and stability.

Learning rate versus loss

The learning-rate curve shows the optimizer step size over time. The loss curve shows prediction error during training. A range test combines both to identify a useful rate region.

Warmup, cycles, and restarts

Warmup reduces early instability, especially with large batches. Cycles periodically raise and lower the rate. Restarts can help the optimizer leave shallow regions.

Common mistakes

A rate can decay too early, remain too high, or become effectively zero. Warmup can also consume too much training. Compare curves before committing expensive training time.

Frequently asked questions

What does a learning-rate curve show?

It shows how the optimizer learning rate changes during training.

Is this the same as a learning curve?

No. A learning curve usually displays training or validation performance.

When should warmup be used?

Warmup is useful for large batches, transformers, and unstable early training.

Why use logarithmic scaling?

Learning rates often span several orders of magnitude.

What is a good Adam learning rate?

It depends on the model and data, so test a reasonable range.

What is the one-cycle policy?

It raises the rate toward one peak, then decreases it strongly.

How is the suggested range-test rate found?

The calculator evaluates smoothed loss gradients and minimum-loss regions.

Can I compare several schedules?

Yes. Enable comparison cards and select independent methods.

Can custom CSV data be used?

Yes. Import x, learning-rate, and optional loss columns.

Does the calculator train a real model?

No. It visualizes schedules and analyzes supplied or simulated values.

Related Calculators

Neural Network Architecture DiagramNeuron Activation PlotActivation Function GraphLoss Landscape PlotGradient Distribution HistogramWeight Distribution HistogramGradient Flow PlotAttention HeatmapEmbedding Projection PlotConvolution Feature Map

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.