Step 6000
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Step 6000 has 30 facts recorded in Dontopedia across 3 references, with 1 live disagreement.
Mostly:has tokens per second(2), has bpb(2), has gradient norm(2)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (6)
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.
atStepAt Step(1)
- AI Training Process
ex:ai-training-process
includesStepIncludes Step(1)
- Analytical Training Session
ex:analytical-training-session
precedesStepPrecedes Step(1)
- Step 3000
ex:step-3000
precedesTemporallyPrecedes Temporally(1)
- Step 5100
ex:step-5100
resumedCleanlyFromResumed Cleanly From(1)
- AI Training Process
ex:ai-training-process
savedFromStepSaved From Step(1)
- Checkpoint
ex:checkpoint
Other facts (30)
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 Tokens Per Second | 13004 | [1] |
| Has Tokens Per Second | 71831 | [2] |
| Has Bpb | 9.191 | [2] |
| Has Bpb | 9.191 | [3] |
| Has Gradient Norm | 496.37 | [2] |
| Has Gradient Norm | 496.37 | [3] |
| Has Loss | 6.371 | [2] |
| Has Loss | 6.371 | [3] |
| Has Progress Percentage | 36 | [1] |
| Has Loss Value | 6.3526 | [1] |
| Follows Sequentially | Step 5100 | [1] |
| Is Out of Total Steps | 16670 | [1] |
| Has Step Duration | 630ms | [1] |
| Has Learning Rate | 0.0000767 | [1] |
| Has Estimated Time Remaining | 112min | [1] |
| Has Perplexity | 574 | [1] |
| Has Omega Component4 | 0.301 | [2] |
| Has Omega Component5 | 0.061 | [2] |
| Has Omega Component6 | 0.26 | [2] |
| Has Omega Component2 | -0.027 | [2] |
| Has Cache Hit Percentage | 99.2 | [2] |
| Has Cache Size | 500 | [2] |
| Has Gamma | 0 | [2] |
| Has Omega Component1 | 0.213 | [2] |
| Has Omega Component3 | 0.262 | [2] |
| Precedes Step | Step 9000 | [2] |
| Rdf:type | Training Step | [3] |
| Step Index | 6000 | [3] |
| Has Token Speed | 71831 | [3] |
| Has Cache Hit Rate | 99.2 | [3] |
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 (3)
ctx:discord/blah/watt-activation/part-130ctx:discord/blah/watt-activation/part-482ctx:discord/blah/watt-activation/480- full textwatt-activation-480text/plain2 KB
doc:agent/watt-activation-480/f2254c38-e451-4fa5-9d6b-499a16b05da3Show excerpt
[2026-03-21 23:19] xenonfun: ``` === BPE-8K: cache growth 200→2000 === Loaded 20480128 bytes from /Users/ms/MS/HarmonicMLX/data/fineweb_edu_bpe8k.npy KickModel ANALYTICAL training: 30000 steps, seq_len=128, lr=0.0005, momentum=0.9…
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.