For ResNet-110 on CIFAR-10, an initial learning rate of 0.1 was slightly too large for prompt convergence, so the reported run warmed up at 0.01 until training error fell below 80% (about 400 iterations) before returning to 0.1. The paper notes that starting directly at 0.1 eventually crossed 90% error after several epochs and reached similar final accuracy.

For ResNet-110 on CIFAR-10, an initial learning rate of 0.1 was slightly too large for prompt convergence, so the reported run warmed up at 0.01 until training error fell below 80% (about 400 iterations) before returning to 0.1. The paper notes that starting directly at 0.1 eventually crossed 90% error after several epochs and reached similar final accuracy. · CiteArk

Measurement results

0/5 assessed

0 supported0 disputed or conflicting5 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Reported	Latest observation	Evidence judgment
0.01 dimensionless	—	Not assessed
0.1 dimensionless	—	Not assessed
80%	—	Not assessed
400 iterations	—	Not assessed
90%	—	Not assessed

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results