SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.08081 · 2024

Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.08081.json · badge: /api/ran/2410.08081.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
shuhewang1998/packing-analysis canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
count_ Ran
ran; our contract draft was wrong, not the code
shuhewang1998/packing-analysis/transfer_data.py
pointer only (licence: NONE) · get_code("a327d99cb3e3eb01")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shuhewang1998/packing-analysis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_score_evaluation_response Ran
ran on a synthesized input
shuhewang1998/packing-analysis/src/llmtuner/api/chat.py
pointer only (licence: NONE) · get_code("3f5cda900eb73d2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shuhewang1998/packing-analysis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dictify Ran
ran; our contract draft was wrong, not the code
shuhewang1998/packing-analysis/src/llmtuner/api/common.py
pointer only (licence: NONE) · get_code("87aa9acaa81294f5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shuhewang1998/packing-analysis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

jsonify Ran
ran; our contract draft was wrong, not the code
shuhewang1998/packing-analysis/src/llmtuner/api/common.py
pointer only (licence: NONE) · get_code("57583cf880d95444")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shuhewang1998/packing-analysis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_json Ran
ran; our contract draft was wrong, not the code
shuhewang1998/packing-analysis/transfer_data.py
pointer only (licence: NONE) · get_code("6e77ca7986aa53f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shuhewang1998/packing-analysis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_jsonl Ran
ran; our contract draft was wrong, not the code
shuhewang1998/packing-analysis/transfer_data.py
pointer only (licence: NONE) · get_code("acd6bebe90eafbda")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shuhewang1998/packing-analysis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
jsonify 28 other papers
6 dated earlier, 2 the same month, 20 later
2403.13372 (2024-03)
LLAMAFACTORY: Unified Efficient Fine-Tuning of 100+ Language Models
2405.04760 (2024-05)
Large Language Models for Cyber Security: A Systematic Literature Review
2406.04496 (2024-06)
Time Sensitive Knowledge Editing through Efficient Finetuning
and 25 more not named here
dictify 14 other papers
4 dated earlier, 2 the same month, 8 later
2403.13372 (2024-03)
LLAMAFACTORY: Unified Efficient Fine-Tuning of 100+ Language Models
2407.08044 (2024-07)
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
2409.13183 (2024-09)
$\textit{SKIntern}$: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models
and 11 more not named here
create_score_evaluation_response 5 other papers
3 dated earlier, 1 the same month, 1 later
2407.08044 (2024-07)
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
2409.13183 (2024-09)
$\textit{SKIntern}$: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models
2409.13203 (2024-09)
Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
and 2 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Packing, initially utilized in the pre-training phase, is an optimization technique designed to maximize hardware resource efficiency by combining different training sequences to fit the model's maximum input length. Although it has demonstrated effectiveness during pre-training, there remains a lack of comprehensive analysis for the supervised fine-tuning (SFT) stage on the following points: (1) whether packing can effectively enhance training efficiency while maintaining performance, (2) the suitable size of the model and dataset for fine-tuning with the packing method, and (3) whether packing unrelated or related training samples might cause the model to either excessively disregard or over-rely on the context. In this paper, we perform extensive comparisons between SFT methods using padding and packing, covering SFT datasets ranging from 69K to 1.2M and models from 8B to 70B. This provides the first comprehensive analysis of the advantages and limitations of packing versus padding, as well as practical considerations for implementing packing in various training scenarios. Our analysis covers various benchmarks, including knowledge, reasoning, and coding, as well as GPT-based evaluations, time efficiency, and other fine-tuning parameters. We also open-source our code for fine-tuning and evaluation and provide checkpoints fine-tuned on datasets of different sizes, aiming to advance future research on packing methods. Code is available at: https://github.com/ShuheWang1998/Packing-Analysis?tab=readme-ov-file.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.08081")
get_code_for_paper("2410.08081")
have("2410.08081")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.08081.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.08081.svg)](https://syntology.ai/paper/2410.08081)

Connect an agent — have() is free.