Tuning YOLO training: read curves before hyperparameters

Tuning is inference: observe a symptom, deduce a cause. Reading curves is the cheapest observation available — provided you know what to look for.

Easy Trainer Station is in development. The method below is what it is built around, and it applies to command-line training too.

Read three curves

Training loss: steady decline is normal; heavy oscillation suggests too high a learning rate or too small a batch.
Validation loss: rising while training loss falls is the classic overfitting shape.
mAP@0.5 vs mAP@0.5:0.95: if the strict metric stalls while the loose one climbs, localization is the bottleneck, not classification.

Check whether augmentation is too aggressive

Strong augmentation slows early training noticeably. If training loss stays high while validation looks fine, suspect augmentation strength before model capacity.

Then change one thing at a time

Learning rate — change only this, run twenty epochs, look at the trend.
Batch size — bounded by memory; use the largest that fits, then consider gradient accumulation.
Input resolution — raise it when small objects matter, remembering inference cost must fit the deployment hardware.
Model scale — change the backbone last; it moves accuracy and speed together.

One variable per run, or the result tells you nothing.

Know when to stop

Early stopping is not “looks about done”. It is a defined patience window on the validation metric. Keep a test split that never participates in tuning, otherwise your numbers are optimistic by construction.

Keep the history

Same data, different parameters, a week apart — without records you cannot tell which checkpoint is which. Weights, run history and notes belong together. That is the main argument for moving training into an interface: you need to know why this run beat the last one.

Progress notes on the Easy Trainer Station product page.