DocsAI Training Coach📈 Reading Training Curves

Interpreting Loss Curves

The heart of training monitoring

The loss curve is your most important diagnostic tool. A trained eye can tell within seconds whether training is healthy, problems are emerging, or immediate action is needed.

Anatomy of a loss curve

X-axis: Time

Training steps or epochs. Further right means longer training. Steps give more granularity.

Y-axis: Loss value

The model's error. Lower = better. Goal: drop to a low, stable level as quickly as possible.

Training Loss (purple)

Error on training data. Calculated after every batch. Often somewhat noisy due to stochasticity.

Validation Loss (dashed)

Error on validation data. Smoother than training loss. The decisive indicator of real performance.

The 4 fundamental loss curve patterns

Good training: train and val loss decrease together

EpochsLoss1.00.60.30.1Train LossVal Losssmall gap

Good training: Both curves drop steadily and converge to a low value. Small, stable gap between training and validation loss. It flattens out at the end (plateau).

Overfitting: val loss rises again

EpochsLossoverfittingstarts hereTrain LossVal Loss

Overfitting: Training loss keeps dropping, validation loss starts to rise. The divergence point marks the optimal training time (early stopping!)

Underfitting: both curves stagnate at a high level

EpochsLossstagnatesTrain LossVal Loss

Underfitting: Both curves stagnate at a high level. The model isn't learning the patterns. Causes: LR too low, too few epochs, wrong model.

Learning rate too high: loss jumps around uncontrollably

EpochsLossunstable, oscillatingTrain Loss

Unstable training (LR too high): Strong oscillation, no convergence. The optimizer keeps overshooting the minimum. Solution: reduce LR.

Benchmarks for "good" loss values

Cross-entropy (binary classification)< 0.2~ 0.2–0.5> 0.5
Cross-entropy (multi-class)< 0.5~ 0.5–1.0> 1.0
Cross-entropy (LLM / language model)< 1.5~ 1.5–3.0> 3.0
Perplexity (LLM)< 10~ 10–50> 50
MSE (normalized data)< 0.05~ 0.05–0.2> 0.2

Note: Absolute values depend heavily on task and model. Trend and comparison matter more than absolute numbers.

Reading loss curves in FrameTrain

In the FrameTrain monitoring panel you see training loss and validation loss in real time. The dashboard shows both steps and epochs on the X-axis. Base your actions on the validation loss — not the training loss!