tu_nlp_byte_mamba3 — Byte × Mamba-3
Source-owned OA v0.12.0 SDK tutorial. Recorded results qualify the named device and driver.
The byte-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 256-token packed-U8 byte vocabulary (ByteSampler) — one token per source byte |
| Model | Byte Embedding → Mamba-3(32,state=32,expand=2) + residual → Linear(32→256) |
| Parameters | 25,800 |
| 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 |
|---|---|---|---|---|
| 5.539→0.214 | 93.0% | 34 | 11.68 | 87.7K |
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_byte_mamba3
Regenerate the training-loss image from the repository root:
cargo run --release -p sdk --example tu_nlp_byte_mamba3 -- --plot sdk/rs/tutorials/ml/nlp/tu_nlp_byte_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 — Byte Mamba-3 · all-position LM (autograd) ║╚══════════════════════════════════════════════════════════════════╝tokenizer: raw bytes · vocab=256Task: dense next-byte prediction at every positionModel: Byte Embedding → Mamba-3(32,state=32,expand=2) + residual → Linear(32→256)params: 25800 Optimizer: AdamW(lr=0.003)300/300 |██████████| 3.64s · 12.15 ms/step · 5.27K sample/s · 84.30K byte token/s · 84.30K byte/s · loss: 0.2143Summary:loss: initial 5.539418 · final 0.214324 · mean 1.149250Wall: 12.15 ms/step · 5.27K sample/s · 84.30K byte token/s · 84.30K byte/sGPU (byte_mamba3_training_step): mean 10.957 ms/step · p50 9.178 · p95 17.094 · min 7.119 · max 18.998 · 5.84K sample/s · 93.46K byte token/s · 93.46K byte/s · wall-GPU gap 10%run: 3.64s · 300 steps · batch 64 · sequence 16 byte token/sampleEvaluation:Random-loss baseline ln(256) = 5.5452byte-token accuracy: 93.0%post-update evaluation loss: 0.207903Generation: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 uploadscheckpoint: optimizer step, accuracy, and exact generation restored