Walk through one training example for SFT'ing a single weather-tool call.

Attempt it

A team wants to fine-tune a 7B chat model so it reliably calls a single `get_weather(city)` tool. Write out, end to end, what ONE training row in the SFT JSONL looks like, the message turns, the roles, what gets masked from the loss, and at least one important negative example you'd also include. Explain why each piece is there.

Free · 2 AI evals / day

**One training row** is a short scripted conversation that shows the model exactly what to do when a user asks a tool-shaped question. For the weather example, the row has four turns. First the user asks something like What is the weather in Paris right now. Second the assistant emits a tool call: a small structured object that names the tool and lists its arguments, in this case the city. Third a tool turn carries the deterministic response from the API, for example temperature 18 and condition cloudy. Fourth the assistant writes the final natural-language reply that quotes those numbers back to the user. Loss masking decides which tokens the model actually learns to predict. The user turn is masked because the model is not supposed to learn to write user messages. The tool turn is masked because the model is not supposed to invent the API response. Loss is computed only on the two assistant turns: the call turn teaches when and how to call, and the final turn teaches how to ground the answer in the returned numbers. The dataset must also include negative rows. A negative is a question that has no tool answer, like What is the capital of France, paired with a plain-text assistant reply and no tool call. Without negatives, the model learns to call the tool for every question.

**A single training row** is a multi-turn JSONL object whose messages array encodes one end to end demonstration of the behaviour you want. For a positive weather example the array has four entries. The user turn is the natural-language question. The first assistant turn carries no free-text content and instead carries a tool call object naming get_weather and serialising its arguments, for instance city Paris. The next turn uses the tool role and carries the deterministic API response, for instance temp_c 18 and condition cloudy, keyed back to the call. The second assistant turn is the final reply, a sentence like It is 18 degrees C and cloudy in Paris. Loss is masked on the user turn and on the tool turn. The user turn would teach the model to imitate users, which is useless. The tool turn would teach the model to invent API responses, which is dangerous because at inference time the real API supplies that string. Loss runs only on the two assistant turns: the call turn teaches when to invoke the tool and what arguments to pass, the final turn teaches how to ground the answer in the returned numbers rather than hallucinating them. The dataset also needs negatives. A negative row is a question like What is the capital of France with a plain-text assistant reply and no tool call. Aim for roughly 30 to 40% negatives, or the model learns the lazy heuristic any question equals call the tool.

Quick reference

TL;DR

A positive row is four turns: user, assistant tool call, tool result, assistant grounded reply. Loss runs only on the two assistant turns, and the dataset must include negatives so the tool is not called for everything.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Picture training a new librarian to use one reference book. You stage a conversation where someone asks a real reference question, the librarian flips open the book, the book shows the page, and the librarian reads the answer aloud. You grade the librarian only on two moments: opening the right book and explaining the right page in plain words. You do not grade what the patron said or what the book literally printed. You also stage other conversations where the patron asks something the book cannot answer, and you teach the librarian to just talk normally without grabbing the book. Without those second kinds of conversations, the librarian learns to grab the book for every question and looks silly when someone asks the time.

Key concepts

Tool calling Supervised fine-tuning Loss masking Negative examples

Detailed answer & concept explanation

~8 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Sign in for 5 free unlocks/day or go Pro for unlimited. See Pro pricing.

Quick scan · 2–4 min

Everything important, quickly.

5 min: four-turn row shape + role of each turn + loss masking on user and tool turns + why both assistant turns matter + negative rows for over-invocation + argument variety + scaling considerations.

Real-world examples

Real products, models, and research that use this idea.

OpenAI's hosted fine-tuning API for gpt-5.5-class tool-calling models accepts JSONL with exactly this four-turn shape and rejects rows that put tool output under the assistant role.
Anthropic's Claude Opus 4.7 tool-use API uses a similar messages contract, with tool_use and tool_result blocks distinguishing the two non-natural language turns.
Hugging Face TRL's SFTTrainer supports chat templates that automatically mask user and tool turns when the role-marker format matches the model's tokenizer config.
Berkeley's Gorilla and Toolformer projects established the convention that negative rows are essential for stable tool-call SFT, a pattern every 2026 production stack now follows.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow would you scale this design from one tool to a fleet of fifty tools?

Sign in or go Pro to see the approach for this follow-up.

QWhat changes if you also want to teach parallel tool calls in one assistant turn?

Sign in or go Pro to see the approach for this follow-up.

QWhy is varying the argument value across positives more important than varying the wording of the user turn?

Sign in or go Pro to see the approach for this follow-up.

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Training only on positives where the tool is called. The model latches on to the shape question equals tool call and starts firing get_weather at trivia questions, the classic over-invocation failure mode.

Sign in or go Pro to see all red flags and common mistakes. See Pro pricing.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.