Saved in:
Bibliographic Details
Main Author: Victor Manuel López González
Format: Recurso digital
Language:En
Published: Zenodo 2026
Subjects:
Online Access:https://doi.org/10.57967/hf/7712
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901705355952128
author Victor Manuel López González
author_facet Victor Manuel López González
contents <p>We present Yuuki-best, an experimental demonstration that large language model fine-tuning is technically feasible on consumer mobile hardware without GPU acceleration or cloud resources. Using a Redmi 12 smartphone (Snapdragon 685 CPU, 6GB RAM) with zero computational budget, we fine-tuned GPT-2 (124M parameters) on 75,000 code samples over 50+ continuous hours. </p> <p> </p> <p>Our investigation reveals three key findings: (1) Loss-quality divergence: checkpoint 2700 achieved 19% lower training loss than checkpoint 2000 but scored 12% worse in code generation quality, challenging the assumption that lower loss guarantees better performance; (2) Dataset ordering effects: alphabetically-early languages (Agda: 55/100 quality) substantially outperformed later languages (Python: 8/100) at identical training progress, demonstrating unintended curriculum learning; (3) Non-monotonic quality patterns: optimal checkpoints occurred mid-training rather than at convergence, with checkpoint 2000 outperforming all subsequent checkpoints through step 2700. </p> <p> </p> <p>While not production-ready (average quality: 24.6/100), this work demonstrates that meaningful ML experimentation is accessible without traditional computational infrastructure, provides empirical evidence of loss-quality divergence in heterogeneous code datasets, and quantifies the impact of dataset ordering on multilingual model training.</p> <p> </p> <p>Model available at: https://huggingface.co/OpceanAI/Yuuki-best</p>
format Recurso digital
id zenodo_https___doi_org_10_57967_hf_7712
institution Zenodo
language enc
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Yuuki-paper
Victor Manuel López González
Llm
AI
<p>We present Yuuki-best, an experimental demonstration that large language model fine-tuning is technically feasible on consumer mobile hardware without GPU acceleration or cloud resources. Using a Redmi 12 smartphone (Snapdragon 685 CPU, 6GB RAM) with zero computational budget, we fine-tuned GPT-2 (124M parameters) on 75,000 code samples over 50+ continuous hours. </p> <p> </p> <p>Our investigation reveals three key findings: (1) Loss-quality divergence: checkpoint 2700 achieved 19% lower training loss than checkpoint 2000 but scored 12% worse in code generation quality, challenging the assumption that lower loss guarantees better performance; (2) Dataset ordering effects: alphabetically-early languages (Agda: 55/100 quality) substantially outperformed later languages (Python: 8/100) at identical training progress, demonstrating unintended curriculum learning; (3) Non-monotonic quality patterns: optimal checkpoints occurred mid-training rather than at convergence, with checkpoint 2000 outperforming all subsequent checkpoints through step 2700. </p> <p> </p> <p>While not production-ready (average quality: 24.6/100), this work demonstrates that meaningful ML experimentation is accessible without traditional computational infrastructure, provides empirical evidence of loss-quality divergence in heterogeneous code datasets, and quantifies the impact of dataset ordering on multilingual model training.</p> <p> </p> <p>Model available at: https://huggingface.co/OpceanAI/Yuuki-best</p>
title Yuuki-paper
topic Llm
AI
url https://doi.org/10.57967/hf/7712