Training Step 14000
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Training Step 14000 has 15 facts recorded in Dontopedia across 2 references.
Mostly:has loss(2), tok per s(1), has ppl(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (1)
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.
savedFromStepSaved From Step(1)
- Checkpoint
ex:checkpoint
Other facts (15)
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.
| Predicate | Value | Ref |
|---|---|---|
| Has Loss | 5.8552 | [1] |
| Has Loss | 5.8552 | [2] |
| Tok Per S | 12290 | [1] |
| Has Ppl | 349 | [1] |
| Progress Percent | 83.9 | [1] |
| Step Time Ms | 667 | [1] |
| Eta Min | 30 | [1] |
| Rdf:type | Training Step | [2] |
| Step Index | 14000 | [2] |
| Progress Percentage | 83.9 | [2] |
| Has Perplexity | 349 | [2] |
| Has Learning Rate | 0.00000272 | [2] |
| Has Duration | 667 | [2] |
| Has Throughput | 12290 | [2] |
| Has Estimated Time Remaining | 30min | [2] |
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.
References (2)
ctx:discord/blah/watt-activation/part-160ctx:discord/blah/watt-activation/160- full textwatt-activation-160text/plain2 KB
doc:agent/watt-activation-160/83f1326e-5f35-47f2-901e-bb1cc61a1eaeShow excerpt
[2026-03-09 16:37] xenonfun: ⏺ With dropout=0.0, the dropout layers are no-ops — they pass through unchanged during both training and inference. So model.train(False) vs model.train(True) makes no difference for our current config. It …
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.