SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.12178 · EMNLP · 2024

Model Balancing Helps Low-data Training and Fine-tuning

Tianyu Pang, Pu Ren, Yaoqing Yang, Yefan Zhou, Zihang Liu, Yuanzhe Hu

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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; 5 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2410.12178.json · badge: /api/ran/2410.12178.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
zihanghliu/modelbalancing canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
gelu_fast Ran
ran, honoured the contract we drafted
zihanghliu/modelbalancing/transformers/src/transformers/activations_tf.py
pointer only (licence: NONE); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("37a5eed2dbd663ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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.

get_config_class_from_processor_class Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zihanghliu/modelbalancing/transformers/utils/create_dummy_models.py
pointer only (licence: NONE); the stored copy get_code serves, from takagi97/OXA-Fine-tuning, is pointer only (licence: NONE) · get_code("3d999b95009c7537")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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.

get_processor_types_from_config_class Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zihanghliu/modelbalancing/transformers/utils/create_dummy_models.py
pointer only (licence: NONE); the stored copy get_code serves, from takagi97/OXA-Fine-tuning, is pointer only (licence: NONE) · get_code("0c0b81b081919d8e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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.

hertz_to_mel Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zihanghliu/modelbalancing/transformers/src/transformers/audio_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("9a09cbf63a4ddff4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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.

inverse_metrics Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zihanghliu/modelbalancing/sciml/pdebench/models/metrics.py
pointer only (licence: NONE) · get_code("73b1d8b8ee56ade1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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.

mel_filter_bank Ran
ran, honoured the contract we drafted
zihanghliu/modelbalancing/transformers/src/transformers/audio_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("7e7c601df5b22499")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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.

mel_to_hertz Ran
ran, honoured the contract we drafted
zihanghliu/modelbalancing/transformers/src/transformers/audio_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("2650530d2f0dd9b2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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.

metric_func Ran
ran; our contract draft was wrong, not the code
zihanghliu/modelbalancing/sciml/pdebench/models/metrics.py
pointer only (licence: NONE) · get_code("866c2ba03b2619cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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.

mish Ran
ran, honoured the contract we drafted
zihanghliu/modelbalancing/transformers/src/transformers/activations_tf.py
pointer only (licence: NONE); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("cc8c8c3ebf0c343f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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.

quick_gelu Ran
ran, honoured the contract we drafted
zihanghliu/modelbalancing/transformers/src/transformers/activations_tf.py
pointer only (licence: NONE); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("e2d56cb91f999bef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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.

get_architectures_from_config_class Not yet run
unverified (harvested, no recorded run)
zihanghliu/modelbalancing/transformers/utils/create_dummy_models.py
pointer only (licence: NONE); the stored copy get_code serves, from takagi97/OXA-Fine-tuning, is pointer only (licence: NONE) · get_code("b176efb26f72e507")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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. No invocation recorded.

metrics Not yet run
unverified (harvested, no recorded run)
zihanghliu/modelbalancing/sciml/pdebench/models/metrics.py
pointer only (licence: NONE) · get_code("c62bfade3b1b51b2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zihanghliu/modelbalancing 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 9 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
get_config_class_from_processor_class 27 other papers
14 dated earlier, 1 the same month, 10 later, 2 same year, order not determinable
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2308.12219 (2023-08)
Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
2311.07468 (2023-11)
An Analysis and Mitigation of the Reversal Curse
and 24 more not named here
get_architectures_from_config_class 25 other papers
13 dated earlier, 1 the same month, 10 later, 1 same year, order not determinable
2308.12219 (2023-08)
Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
2311.07468 (2023-11)
An Analysis and Mitigation of the Reversal Curse
2312.15710 (2023-12)
Alleviating Hallucinations of Large Language Models through Induced Hallucinations
and 22 more not named here
get_processor_types_from_config_class 25 other papers
13 dated earlier, 1 the same month, 10 later, 1 same year, order not determinable
2308.12219 (2023-08)
Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
2311.07468 (2023-11)
An Analysis and Mitigation of the Reversal Curse
2312.15710 (2023-12)
Alleviating Hallucinations of Large Language Models through Induced Hallucinations
and 22 more not named here
mish 25 other papers
23 dated earlier, 1 the same month, 1 same year, order not determinable
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2106.00420 (2021-06)
Dialogue-oriented Pre-training
and 22 more not named here
gelu_fast 19 other papers
17 dated earlier, 1 the same month, 1 same year, order not determinable
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2110.04366 (2021-10)
Towards a Unified View of Parameter-Efficient Transfer Learning
2111.00160 (2021-11)
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
and 16 more not named here
quick_gelu 16 other papers
14 dated earlier, 1 the same month, 1 same year, order not determinable
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2202.00666 (2022-02)
Locally Typical Sampling
2211.05392 (2022-11)
EVENTS REALM: Event Reasoning of Entity States via Language Models
and 13 more not named here
hertz_to_mel 5 other papers
3 dated earlier, 1 the same month, 1 same year, order not determinable
2311.07468 (2023-11)
An Analysis and Mitigation of the Reversal Curse
2024.findings-naacl.117 (2024 (year only))
Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
2402.18223 (2024-02)
Improving Open-Ended Text Generation via Adaptive Decoding
and 2 more not named here
mel_to_hertz 5 other papers
3 dated earlier, 1 the same month, 1 same year, order not determinable
2311.07468 (2023-11)
An Analysis and Mitigation of the Reversal Curse
2024.findings-naacl.117 (2024 (year only))
Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
2402.18223 (2024-02)
Improving Open-Ended Text Generation via Adaptive Decoding
and 2 more not named here
mel_filter_bank 4 other papers
2 dated earlier, 1 the same month, 1 same year, order not determinable
2311.07468 (2023-11)
An Analysis and Mitigation of the Reversal Curse
2024.findings-naacl.117 (2024 (year only))
Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
2404.16367 (2024-04)
Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers
and 1 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Recent advances in foundation models have emphasized the need to align pre-trained models with specialized domains using small, curated datasets. Studies on these foundation models underscore the importance of low-data training and fine-tuning. This topic, well-known in natural language processing (NLP), has also gained increasing attention in the emerging field of scientific machine learning (SciML). To address the limitations of low-data training and fine-tuning, we draw inspiration from Heavy-Tailed Self-Regularization (HT-SR) theory, analyzing the shape of empirical spectral densities (ESDs) and revealing an imbalance in training quality across different model layers. To mitigate this issue, we adapt a recently proposed layer-wise learning rate scheduler, TempBalance, which effectively balances training quality across layers and enhances low-data training and fine-tuning for both NLP and SciML tasks. Notably, TempBalance demonstrates increasing performance gains as the amount of available tuning data decreases. Comparative analyses further highlight the effectiveness of TempBalance and its adaptability as an "add-on" method for improving model performance. * Equal contribution. Work completed during an internship at Dartmouth College. Imbalanced Before Using TempBalance Smaller PL_Alpha_Hill Schedule Smaller LR Larger PL_Alpha_Hill Schedule Larger LR PL_Alpha_Hill Layer/Block Index ESD of weight matrices PL_Alpha_Hill Layer/Block Index RoBERTa-base accuracy on 0.2% SST-2: 58.49 RoBERTa-base accuracy on 0.2% SST-2: 68.39 Less Heavy-tailed More Heavy-tailed More Balanced After Using TempBalance

For agents

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

get_harvested_code_for_paper("2410.12178")
get_code_for_paper("2410.12178")
have("2410.12178")

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

curl https://syntology.ai/api/ran/2410.12178.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.12178.svg)](https://syntology.ai/paper/2410.12178)

Connect an agent — have() is free.