PhyloGPN training compute
Training compute of PhyloGPN
Eighteen epochs on four NVIDIA A100 GPUs with AdamW, a fixed learning rate of 1e-5 and no weight decay; 12 alignment blocks of about 10 kb per batch, with autosomal positions sampled four times per epoch, X chromosome positions three times and Y chromosome positions once.
The hardware, optimiser and schedule PhyloGPN was trained with.
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.
6 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Claimed field training_compute Context-only references | A Phylogenetic Approach to Genomic Language Modeling Methods, Architecture and Training (paragraphs 2-3) Version: preprint version in PMC | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Source location Methods, Architecture and Training (paragraphs 2-3) Context-only references | A Phylogenetic Approach to Genomic Language Modeling Methods, Architecture and Training (paragraphs 2-3) Version: preprint version in PMC | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Claimed value Eighteen epochs on four NVIDIA A100 GPUs with AdamW, a fixed learning rate of 1e-5 and no weight decay; 12 alignment blocks of about 10 kb per batch, with autosomal positions sampled four times per epoch, X chromosome positions three times and Y chromosome positions once. Context-only references | A Phylogenetic Approach to Genomic Language Modeling Methods, Architecture and Training (paragraphs 2-3) Version: preprint version in PMC | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Description The hardware, optimiser and schedule PhyloGPN was trained with. Context-only references | A Phylogenetic Approach to Genomic Language Modeling Methods, Architecture and Training (paragraphs 2-3) Version: preprint version in PMC | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Relationship: subject lit-genomics-20261011-guanine-model-phylogpn Context-only references | A Phylogenetic Approach to Genomic Language Modeling Methods, Architecture and Training (paragraphs 2-3) Version: preprint version in PMC | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Name PhyloGPN training compute Context-only references | A Phylogenetic Approach to Genomic Language Modeling Methods, Architecture and Training (paragraphs 2-3) Version: preprint version in PMC | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
1 source record and release history
- A Phylogenetic Approach to Genomic Language Modeling · Original source · preprint version in PMC
Technical metadata and extraction receipts
Stable ID: phylogpn-20261116-claim-training-compute
- areas
- dna-genomes
- contexts
- research
- field
- training_compute
- value
- Eighteen epochs on four NVIDIA A100 GPUs with AdamW, a fixed learning rate of 1e-5 and no weight decay; 12 alignment blocks of about 10 kb per batch, with autosomal positions sampled four times per epoch, X chromosome positions three times and Y chromosome positions once.
- source locator
- Methods, Architecture and Training (paragraphs 2-3)
- review
- method: transcription; source-hash-verification; method note: Independent review pass by a different agent from the extractor. Each field was re-read against the pinned artifact at the recorded locator: the Europe PMC full text XML, whose SHA-256 was re-checked, and, where the record cites it, the supplement PDF, whose member hash was re-checked inside a third, differently hashed Europe PMC zip. No number in these records comes from a figure.; reviewer: claude; reviewer note: Claude review agent (independent of the extractor); no human review claimed. Transcription was checked against the pinned sources; nothing was reproduced.; date: 2026-11-16; artifact sha256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC11908359/fullTextXML; note: Re-read against the pinned source at Methods, Architecture and Training (paragraphs 2-3); no change.
Related records
- subject: PhyloGPN