LoheOptimizer+jchain
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
LoheOptimizer+jchain has 15 facts recorded in Dontopedia across 1 reference.
Mostly:rdf:type(1), train loss(1), train perplexity(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound 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.
forOptimizerFor Optimizer(5)
- Lohe Step 1000
ex:lohe-step-1000 - Lohe Step 200
ex:lohe-step-200 - Lohe Step 400
ex:lohe-step-400 - Lohe Step 600
ex:lohe-step-600 - Lohe Step 800
ex:lohe-step-800
comparesOptimizerCompares Optimizer(1)
- Comparison Baseline
ex:comparison-baseline
isSlowerThanIs Slower Than(1)
- Rotational Adamw
ex:rotational-adamw
performsBetterThanPerforms Better Than(1)
- Rotational Adamw
ex:rotational-adamw
Other facts (14)
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 |
|---|---|---|
| Rdf:type | Optimizer | [1] |
| Train Loss | 11.6547 | [1] |
| Train Perplexity | 115234.7 | [1] |
| Validation Loss | 12.3104 | [1] |
| Validation Perplexity | 221983.6 | [1] |
| Tokens Per Second | 14464 | [1] |
| Wall Time Seconds | 283.2 | [1] |
| Val Ppl Difference | 219493.2 | [1] |
| Speed Ratio | 1.33 | [1] |
| First Ten Avg Train Loss | 11.8793 | [1] |
| Mid Ten Avg Train Loss | 12.4665 | [1] |
| Last Ten Avg Train Loss | 11.6811 | [1] |
| Performs Worse Than | Rotational Adamw | [1] |
| Is Faster Than | Rotational Adamw | [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.
References (1)
ctx:discord/blah/watt-activation/213- full textwatt-activation-213text/plain2 KB
doc:agent/watt-activation-213/16ef74b4-a6af-4b66-91eb-9cfddab2b495Show excerpt
[2026-03-11 04:15] xenonfun: oh yeah I knew the loheoptimizer so far only seemed to work on finetune [2026-03-11 04:15] lisamegawatts: yes if it wasn't aware loss would not go down, the rotational adam is fine [2026-03-11 04:16] xenonfun: o…
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.