tu_nlp_bpe_moe — BPE × sparse MoE Transformer
Source-owned OA v0.12.0 SDK tutorial. Recorded results qualify the named device and driver.
The BPE-tokenizer × sparse MoE Transformer 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 320-token learned BPE vocabulary (BpeTokenizer/BpeSampler: 256 bytes + 64 merges) — merges collapse the corpus into short predictable runs, which is why BPE rows reach ~0.02 loss |
| Model | BPE + position Embedding → Attention + MoE(E=4,K=2,DFF=16) → LN → Linear |
| Parameters | 32,228 |
| Optimizer | AdamW(lr=0.01) — the canonical recipe |
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 (62 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 |
|---|---|---|---|---|
| 5.844→0.020 | 98.8% | 62 | 10.43 | 98.2K |
Reference generation on the default recipe (asserted by the tutorial):
1prompt: "to be"2generated: "to bee or not to be that is the question whether tis nobler in the mind to suffer the"3
Run
cargo run --release -p sdk --example tu_nlp_bpe_moe
Regenerate the training-loss image from the repository root:
cargo run --release -p sdk --example tu_nlp_bpe_moe -- --plot sdk/rs/tutorials/ml/nlp/tu_nlp_bpe_moe/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 — BPE MoE Transformer · all-position LM (autograd)║╚══════════════════════════════════════════════════════════════════╝tokenizer: byte BPE · vocab=320 (256 bytes + 64 merges)compression: 576 bytes → 210 tokens · 2.743 byte/token · 63.5% fewer positionscontext coverage: 16 BPE tokens ≈ 43.9 source bytes at corpus averageTask: dense next-token prediction at every positionModel: BPE + position Embedding → Attention + MoE(E=4,K=2,DFF=16) → LN → Linearparams: 32228 Optimizer: AdamW(lr=0.01)300/300 |██████████| 3.01s · 10.02 ms/step · 6.39K sample/s · 102.21K BPE token/s · 283.69K byte/s · loss: 0.0204Summary:loss: initial 5.844332 · final 0.020420 · mean 0.232860Wall: 10.02 ms/step · 6.39K sample/s · 102.21K BPE token/s · 283.68K byte/sGPU (bpe_moe_training_step): mean 8.785 ms/step · p50 6.953 · p95 14.975 · min 5.817 · max 15.641 · 7.29K sample/s · 116.57K BPE token/s · 323.53K byte/s · wall-GPU gap 12%run: 3.01s · 300 steps · batch 64 · sequence 16 BPE token/sampleEvaluation:Random-loss baseline ln(320) = 5.7683final batch: 2.771 byte/token · 0.0106 bits/byteBPE-token accuracy: 98.8%post-update evaluation loss: 0.019962Generation:prompt: "to be"generated: "to bee or not to be that is the question whether tis nobler in the mind to suffer the"program: 62 nodes · 1 recording · 299 cache hits · 0 uploads