Loss Down, Loops Up: Fine-tuning a Gemma 4 31B coding agent on teacher trajectories lowered validation loss and cost solved tasks at both sampling settings we tested

We fine-tuned Gemma 4 31B with a LoRA adapter on 240 successful teacher trajectories converted to the competition's repository-repair harness. Validation loss fell from 0.6375 to 0.2597. On the same 72 solvable FastAPI and Rich tasks, the fine-tuned agent solved fewer tasks than the base model at both sampling settings we ran: 15 versus 29 at temperature 0.2 (exact paired p = 0.00012) and 20 versus 32 at Gemma's recommended sampling of temperature 1.0, top-p 0.95, top-k 64 (p = 0.0075). How it failed depended on sampling. At temperature 0.2 it often submitted nothing (nonempty patches 31 versus 57), and full traces of 20 tasks show repetitive long generations or action loops in 16 fine-tuned runs and no base runs. At temperature 1.0 it submitted as often as the base model (58 versus 58), 11 of the 15 tasks it lost ended with a wrong patch, and the same signatures appeared in 21 of 72 fine-tuned runs versus 3 base runs. At temperature 0.2, instructions, oracle location hints and a doubled budget did not restore patch delivery. We turn these measurements into a pre-deployment check for fine-tuned tool-using agents. Code and data: https://www.kaggle.com/datasets/watermelon696969/gemma4-agent-loss-down-loops-up

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-17
DOI
https://doi.org/10.5281/zenodo.24318927
Primary Topic
Software Engineering Research
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Loss Down, Loops Up: Fine-tuning a Gemma 4 31B coding agent on teacher trajectories lowered validation loss and cost solved tasks at both sampling settings we tested

Chen-Yen Wu
2 links
Zenodo (CERN European Organization for Nuclear Research)
Software Engineering Research
preprint

Loss Down, Loops Up: Fine-tuning a Gemma 4 31B coding agent on teacher trajectories lowered validation loss and cost solved tasks at both sampling settings we tested

Chen-Yen Wu
preprint en

Abstract

We fine-tuned Gemma 4 31B with a LoRA adapter on 240 successful teacher trajectories converted to the competition's repository-repair harness. Validation loss fell from 0.6375 to 0.2597. On the same 72 solvable FastAPI and Rich tasks, the fine-tuned agent solved fewer tasks than the base model at both sampling settings we ran: 15 versus 29 at temperature 0.2 (exact paired p = 0.00012) and 20 versus 32 at Gemma's recommended sampling of temperature 1.0, top-p 0.95, top-k 64 (p = 0.0075). How it failed depended on sampling. At temperature 0.2 it often submitted nothing (nonempty patches 31 versus 57), and full traces of 20 tasks show repetitive long generations or action loops in 16 fine-tuned runs and no base runs. At temperature 1.0 it submitted as often as the base model (58 versus 58), 11 of the 15 tasks it lost ended with a wrong patch, and the same signatures appeared in 21 of 72 fine-tuned runs versus 3 base runs. At temperature 0.2, instructions, oracle location hints and a doubled budget did not restore patch delivery. We turn these measurements into a pre-deployment check for fine-tuned tool-using agents. Code and data: https://www.kaggle.com/datasets/watermelon696969/gemma4-agent-loss-down-loops-up

Zenodo (CERN European Organization for Nuclear Research)
Chung Yuan Christian University (TW)
Software Engineering Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon