Seeded Batch Order for an Epoch
~10 mincode completion
Implement epoch_batches(n, batch_size, seed, epoch) returning an integer array of shape (n // batch_size, batch_size) with the batches of the requested epoch.
Where this shows up
~10 min
••••••••••••••••
8 employers weight this skill
3 quant funds, 2 big tech firms, 1 health and bio company, 1 AI product company, 1 defense company. Top match scores 75.
Python
import numpy as np
def epoch_batches(n, batch_size, seed, epoch):
"""
The batches a seeded training run sees in a given epoch.
Args:
n: number of training examples
batch_size: examples per batch (the incomplete last batch is dropped)
seed: the run's seed for np.random.default_rng
epoch: which epoch, starting at 0
Returns:
integer array of shape (n // batch_size, batch_size)
"""
# YOUR CODE HERE
pass