Protocol

Nucleotide Transformer IA3 fine-tuning run time (Dalla-Torre et al. 2025 Methods 'Hardware')

Average wall time of one parameter-efficient (IA3) fine-tuning run on the downstream tasks.

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

2 recorded evaluations, 2 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

2 evaluations · 2 results. Different protocols are not a single leaderboard.

Protocol: Nucleotide Transformer IA3 fine-tuning run time (Dalla-Torre et al. 2025 Methods 'Hardware') · Dataset: NT benchmark, all 18 tasks

Sorted by Runtime (Mean wall time per IA3 fine-tuning run) (lower is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Runtime (Mean wall time per IA3 fine-tuning run)
Nucleotide Transformer 500M-parameter models, IA3 fine-tuning (Dalla-Torre et al. 2025)Evaluation	20 (best in column)
Nucleotide Transformer 2.5B-parameter models, IA3 fine-tuning (Dalla-Torre et al. 2025)Evaluation	50

All 2 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: Nucleotide Transformer 2.5B-parameter models, IA3 fine-tuning (Dalla-Torre et al. 2025)	Protocol: Nucleotide Transformer IA3 fine-tuning run time (Dalla-Torre et al. 2025 Methods 'Hardware') Dataset: NT benchmark, all 18 tasks	50 Runtime (Mean wall time per IA3 fine-tuning run) minute · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Fine-tuning time conflicts within the article. Methods 'Hardware' say all fine-tuning runs used one node of eight A100 GPUs and averaged 20 min (500M-parameter models) and 50 min (2.5B-parameter models); the Discussion says the IA3 technique allows even the largest models to be fine-tuned in under 15 min on a single GPU. Both are recorded; neither is preferred.Nucleotide Transformer: building and evaluating robust foundation models for human genomics (Nature Methods) · Methods, 'Data preparation > Hardware', paragraph 1; Discussion, paragraph 3 Methods, coverage and source NT 2.5B-parameter models IA3 fine-tuning run time (Dalla-Torre et al. 2025) gfm-guide-20261014-protocol-nt-ia3-finetune-runtime Aggregation: Not reported Nucleotide Transformer: building and evaluating robust foundation models for human genomics (Nature Methods) · Methods, 'Data preparation > Hardware', paragraph 1: 'On average, a fine-tuning run lasted 20 min for the 500M-parameter models and 50 min for the 2.5B-parameter models.'
Configuration: Nucleotide Transformer 500M-parameter models, IA3 fine-tuning (Dalla-Torre et al. 2025)	Protocol: Nucleotide Transformer IA3 fine-tuning run time (Dalla-Torre et al. 2025 Methods 'Hardware') Dataset: NT benchmark, all 18 tasks	20 Runtime (Mean wall time per IA3 fine-tuning run) minute · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Fine-tuning time conflicts within the article. Methods 'Hardware' say all fine-tuning runs used one node of eight A100 GPUs and averaged 20 min (500M-parameter models) and 50 min (2.5B-parameter models); the Discussion says the IA3 technique allows even the largest models to be fine-tuned in under 15 min on a single GPU. Both are recorded; neither is preferred.Nucleotide Transformer: building and evaluating robust foundation models for human genomics (Nature Methods) · Methods, 'Data preparation > Hardware', paragraph 1; Discussion, paragraph 3 Methods, coverage and source NT 500M-parameter models IA3 fine-tuning run time (Dalla-Torre et al. 2025) gfm-guide-20261014-protocol-nt-ia3-finetune-runtime Aggregation: Not reported Nucleotide Transformer: building and evaluating robust foundation models for human genomics (Nature Methods) · Methods, 'Data preparation > Hardware', paragraph 1: 'On average, a fine-tuning run lasted 20 min for the 500M-parameter models and 50 min for the 2.5B-parameter models.'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 2

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Strengths, limitations and unresolved questions

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

Nucleotide Transformer: building and evaluating robust foundation models for human genomics (Nature Methods) · Original source · Nature Methods 22, 287-297 (published online 2024-11-28); PMC11810778 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm-guide-20261014-protocol-nt-ia3-finetune-runtime

areas: dna-genomes
contexts: research
protocol: IA3 fine-tuning on one node of eight A100 GPUs, weights replicated, batch size eight (one sample per GPU); average duration of a fine-tuning run.
version: Nature Methods 2025 Methods
metric: runtime
limitations: Developer-reported average; the number of runs and the tasks averaged over are not stated.; The Discussion's 'under 15 min on a single GPU' conflicts with these values (see the source concern).
source locator: Methods, 'Data preparation > Hardware', paragraph 1

Related records

uses data: NT benchmark, all 18 tasks
assessment: NT 2.5B-parameter models IA3 fine-tuning run time (Dalla-Torre et al. 2025)
assessment: NT 500M-parameter models IA3 fine-tuning run time (Dalla-Torre et al. 2025)
assessed by: Select an execution workflow for large-scale diagnostic genomics

Suggest a correction