Dontopedia

Training Logs

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

Training Logs has 11 facts recorded in Dontopedia across 5 references, with 1 live disagreement.

11 facts·5 predicates·5 sources·1 in dispute

Mostly:has config parameter(7), demonstrate rapid convergence(1), shows stable loss(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (8)

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.

isFasterAtSameSizeIs Faster at Same Size(1)

listsTrainingLogsLists Training Logs(1)

proposesToCompareConfigsProposes to Compare Configs(1)

reportsProgressReports Progress(1)

sharesLogOutputShares Log Output(1)

statedBenchmarkUsedDifferentConfigsStated Benchmark Used Different Configs(1)

storesStores(1)

stores-artifactsStores Artifacts(1)

Other facts (11)

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.

11 facts
PredicateValueRef
Has Config ParameterD Model Param[5]
Has Config ParameterLayers Param[5]
Has Config ParameterHeads Param[5]
Has Config ParameterBs Param[5]
Has Config ParameterSeq Param[5]
Has Config ParameterVocab Param[5]
Has Config ParameterOptimizer Param[5]
Demonstrate Rapid Convergencenull[1]
Shows Stable LossLoss Range 5 8[2]
References Other SweepsTraining Sweeps[3]
Rdf:typeLog Files[4]

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.

11 undated
—
demonstrateRapidConvergenceblah/watt-activation/part-49
null
—
showsStableLossblah/watt-activation/part-160
ex:loss-range-5-8
—
referencesOtherSweepsblah/watt-activation/part-315
ex:training-sweeps
—
typebeam/9500e1c6-ed0c-41a2-ace0-794604c62109
ex:log-files
—
hasConfigParameterblah/watt-activation/313
ex:d_model-param
—
hasConfigParameterblah/watt-activation/313
ex:layers-param
—
hasConfigParameterblah/watt-activation/313
ex:heads-param
—
hasConfigParameterblah/watt-activation/313
ex:bs-param
—
hasConfigParameterblah/watt-activation/313
ex:seq-param
—
hasConfigParameterblah/watt-activation/313
ex:vocab-param
—
hasConfigParameterblah/watt-activation/313
ex:optimizer-param

References (5)

5 references
  1. [1]Part 491 fact
    ctx:discord/blah/watt-activation/part-49
  2. [2]Part 1601 fact
    ctx:discord/blah/watt-activation/part-160
  3. [3]Part 3151 fact
    ctx:discord/blah/watt-activation/part-315
  4. [4]9500e1c6 Ed0c 41a2 Ace0 794604c621091 fact
    ctx:claims/beam/9500e1c6-ed0c-41a2-ace0-794604c62109
    • full textbeam-chunk
      text/plain1 KBdoc:beam/9500e1c6-ed0c-41a2-ace0-794604c62109
      Show excerpt
      - **Strategy**: Use `True` if your hardware supports it (e.g., NVIDIA GPUs with Tensor Cores). ### Example Configuration Here's an example configuration for fine-tuning Llama 2 13B: ```python from transformers import LlamaForCausalLM…
  5. [5]3137 facts
    ctx:discord/blah/watt-activation/313
    • full textwatt-activation-313
      text/plain3 KBdoc:agent/watt-activation-313/cf51bfc5-991d-4ede-bf30-9671c3b0fb08
      Show excerpt
      [2026-03-15 01:25] xenonfun: ⏺ No — the benchmark used different configs than the training logs. Let me compare: ``` ┌───────────┬──────────────────┬──────────────────┐ │ │ Training Logs │ My Benchmark │ ├───────────┼…

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.

↑