Linear-Probe vs Fine-Tune Delta

Problem

Compute how much full fine-tuning improves over a frozen linear probe.

Return round(fine_tune - linear_probe, 4).

case 1

in: [0.72,0.81]

expected: 0.09

case 2

in: [0.5,0.5]

expected: 0

case 3

in: [0.65,0.6]

expected: -0.05

Starter codePython

def probe_finetune_delta(linear_probe, fine_tune):
    # Your code here
    pass

3 test cases · run your code against them in the editor