tu_nlp_char_mamba3 — Character × Mamba-3
Source-owned OA v0.12.0 SDK tutorial. Recorded results qualify the named device and driver.
The character-tokenizer × Mamba-3 cell of the — same 576-character corpus, same 300-step recipe and captured training lifecycle. This entry selects the tokenizer and model shown below. See for the full walkthrough.
This cell
| Tokenizer | the 27-token character vocabulary (CharSampler) — accuracy is comparable within Char rows only |
| Model | Embedding(32) → Mamba-3 SISO → residual → Linear(27) |
| Parameters | 10,915 |
| Optimizer | AdamW(lr=0.003) — lower rate for the Mamba-3/Empyrealm family |
The loop is a prepare/record pair per step — GradientTape → cross_entropy → backward → AdamW —
driven by oa::ml::ItTraining, so the whole run is one captured GPU program replayed
299 times (34 nodes for this model).
Measured — Surface Laptop 5 (ADL GT2)

Canonical 300-step training loss, recorded by this tutorial.
| Loss init→final | Accuracy | Program nodes | Wall ms/step | Token/s |
|---|---|---|---|---|
| 3.303→0.195 | 93.0% | 34 | 10.69 | 95.8K |
Reference generation on the default recipe (asserted by the tutorial):
1prompt: "to be"2generated: "to be that is the question whether tis nobler in the mind to suffer the slings and ar"3
Run
cargo run --release -p sdk --example tu_nlp_char_mamba3cargo run --release -p sdk --example tu_nlp_char_mamba3 -- --plot sdk/rs/tutorials/ml/nlp/tu_nlp_char_mamba3/asset/training-curve.png
On the default recipe the tutorial self-tests: loss regime, accuracy
floor, exact reference generation, and .oam checkpoint round-trip.
Terminal output
Recorded canonical 300-step run on Intel Iris Xe (ADL GT2), Mesa 26.2.7. Startup logs, intermediate progress updates and the plot-save path are omitted. Timings vary by run; these are not new benchmark baselines.
╔══════════════════════════════════════════════════════════════════╗║ OA Tutorial — Char Mamba-3 · all-position LM (autograd) ║╚══════════════════════════════════════════════════════════════════╝tokenizer: character · vocab=27 (a-z + space)Task: dense next-character prediction at every positionModel: Embedding(32) → Mamba-3 SISO → residual → Linear(27)params: 10915 Optimizer: AdamW(lr=0.003)training: 300 steps · batch=64 · sequence=16 character tokens300/300 |██████████| 3.18s · 10.58 ms/step · 6.05K sample/s · 96.74K token/s · loss: 0.1945Summary:loss: initial 3.303064 · final 0.194512 · mean 0.714765Wall: 10.59 ms/step · 6.05K sample/s · 96.74K token/sGPU (char_mamba3_training_step): mean 9.616 ms/step · p50 7.558 · p95 16.954 · min 6.281 · max 20.094 · 6.66K sample/s · 106.49K token/s · wall-GPU gap 9%run: 3.18s · 300 steps · batch 64 · sequence 16 token/sampleEvaluation:Random-loss baseline ln(27) = 3.2958loss: evaluation 0.190578 · last training 0.194512character-token accuracy: 93.0% (compare within Char only)Generation:prompt: "to be"generated: "to be that is the question whether tis nobler in the mind to suffer the slings and ar"program: 34 nodes · 1 recording · 299 cache hits · 0 uploads