Dontopedia

batch_size argument

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-11.)

batch_size argument has 5 facts recorded in Dontopedia across 2 references, with 1 live disagreement.

5 facts·3 predicates·2 sources·1 in dispute
Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (2)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

hasArgumentHas Argument(1)

hasParameterHas Parameter(1)

Other facts (4)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

4 facts
PredicateValueRef
Rdf:typeFunction Argument[1]
Rdf:typeFunction Argument[2]
Has Value32[1]
Inverse Has ValueLoader Variable[1]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

typebeam/16c146b3-4e30-40ba-bda6-27d68d4d4231
ex:FunctionArgument
hasValuebeam/16c146b3-4e30-40ba-bda6-27d68d4d4231
32
inverseHasValuebeam/16c146b3-4e30-40ba-bda6-27d68d4d4231
ex:loader-variable
typebeam/2cbdcf90-9d21-4bed-aea6-acf4a8366428
ex:FunctionArgument
labelbeam/2cbdcf90-9d21-4bed-aea6-acf4a8366428
batch_size argument

References (2)

2 references
  1. ctx:claims/beam/16c146b3-4e30-40ba-bda6-27d68d4d4231
    • full textbeam-chunk
      text/plain1 KBdoc:beam/16c146b3-4e30-40ba-bda6-27d68d4d4231
      Show excerpt
      device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = RerankingModel().to(device) dataset = ... # Your dataset loader = torch.utils.data.DataLoader(dataset, batch_size=32, shuffle=True) optimizer
  2. ctx:claims/beam/2cbdcf90-9d21-4bed-aea6-acf4a8366428
    • full textbeam-chunk
      text/plain1 KBdoc:beam/2cbdcf90-9d21-4bed-aea6-acf4a8366428
      Show excerpt
      futures = [executor.submit(self.model.batch_reformulate, queries[i:i+batch_size]) for i in range(0, len(queries), batch_size)] results = [] for future in as_completed(futures): results.ext

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.