NTv3 H100 GPU-hours per training stage (Boshar et al. 2025 Table 5)
H100 GPU-hours used by each training stage of each NTv3 model size.
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.
3 recorded evaluations, 13 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
3 evaluations · 13 results. Different protocols are not a single leaderboard.
Protocol: NTv3 H100 GPU-hours per training stage (Boshar et al. 2025 Table 5) · Dataset: NTv3 training data, all stages (Boshar et al. 2025)
Sorted by Accelerator time (Training stage 'Length ext. 1-4' (200B tokens)) (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 | Accelerator time (Training stage 'Length ext. 1-4' (200B tokens)) | Accelerator time (Training stage 'Length ext. 5-7' (150B tokens)) | Accelerator time (Training stage 'Pre-training 8 kb' (10.5T tokens)) | Accelerator time (Training stage 'Post-training 1' (1.2T tokens)) | Accelerator time (Training stage 'Post-training 2' (54B tokens)) |
|---|---|---|---|---|---|
| NTv3 100M training run (Boshar et al. 2025)Evaluation | 40 (best in column) | 48 | 3,000 | 1,536 (best in column) | 192 (best in column) |
| NTv3 8M training run (Boshar et al. 2025)Evaluation | 40 (best in column) | 40 (best in column) | 1,608 (best in column) | Not reported | Not reported |
| NTv3 650M training run (Boshar et al. 2025)Evaluation | 88 | 80 | 6,736 | 1,824 | 192 (best in column) |
All 13 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
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
- 3
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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- A foundational model for joint sequence-function multi-species modeling at scale for long-range genomic prediction (NTv3), bioRxiv v1 · Original source · bioRxiv v1, posted 2025-12-25 (dated 2025-12-22 on the title page)
Technical metadata and extraction receipts
Stable ID: gfm-guide-20261014-protocol-ntv3-training-gpu-hours
- areas
- dna-genomes
- contexts
- research
- protocol
- Accelerator time per training stage on the authors' infrastructure (8 × H100 80GB nodes, NVLink, RoCE), as printed in Table 5.
- version
- bioRxiv v1 Table 5
- metric
- accelerator-time
- limitations
- Developer-reported.; The text says models were trained on either Cloud TPU v6 or on-premise H100s; Table 5 gives H100 GPU-hours for every stage without saying whether TPU runs were converted.; Post-training stages are not applicable to the 8M model (printed NA).
- source locator
- Table 5 and section 4.4.4 'Training Infrastructure' (page 34)
Related records
- uses data: NTv3 training data, all stages (Boshar et al. 2025)
- assessment: NTv3 100M training GPU-hours (Boshar et al. 2025 Table 5)
- assessment: NTv3 650M training GPU-hours (Boshar et al. 2025 Table 5)
- assessment: NTv3 8M training GPU-hours (Boshar et al. 2025 Table 5)
- assessed by: Select an execution workflow for large-scale diagnostic genomics