Implement prompt-token loss masking given (prompt_len, total_len) per sample

Easy

SFT, Instruction Tuning & PEFT1 / 6

Chapter 111 / 6

SFT, Instruction Tuning & PEFT

Implement prompt-token loss masking given (prompt_len, total_len) per sample

Easy

Target interface

build_labels(input_ids, prompt_len, total_len)

Implement the function/class skeleton in the editor. Any correct approach is accepted.

Hints0 / 2

Reference solution

Your own code stays in the editor.

solution.pyPython

Local draft

import torch

def build_labels(input_ids, prompt_len, total_len):
    raise NotImplementedError

def masked_lm_loss(logits, labels):
    raise NotImplementedError

⌘/Ctrl↵to submit

AI review

No review yet

Submit your solution for a verdict, a score out of 100 and concrete feedback. Any correct approach passes.

Chapter 111 / 6

SFT, Instruction Tuning & PEFT

Implement prompt-token loss masking given (prompt_len, total_len) per sample

Easy

Target interface

build_labels(input_ids, prompt_len, total_len)

Implement the function/class skeleton in the editor. Any correct approach is accepted.

Hints0 / 2

Reference solution

Your own code stays in the editor.