From e05521482f2cd15c7e242f6b80dcb653a6519cbb Mon Sep 17 00:00:00 2001 From: Nucleic Date: Thu, 30 Jul 2026 20:42:39 -0700 Subject: [PATCH] Merge nucleic/sleek-ember-seal-uady into dev --- README.md | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index f2b6c3f..1d0f37d 100644 --- a/README.md +++ b/README.md @@ -110,7 +110,7 @@ ml/purpose-classifier/.venv/bin/python ml/purpose-classifier/train.py \ On dataset v1, that validation-selected run produced a 23,148,500-byte int8 graph at 94.88% frozen accuracy (889/937), 94.46% scored-hard accuracy, and 98.19% scorable -PyTorch↔ONNX agreement. It is the current quantized candidate, but remains two correct +PyTorch↔ONNX agreement. It was the pre-distillation quantized candidate and remained two correct predictions below the 95% gate. A subsequent validation-selected `5e-7` epoch improved int8 validation accuracy from 93.31% to 93.71% but regressed frozen accuracy to 94.34%; it is rejected. Do not continue optimizer-only QAT sweeps on this split. The next model @@ -181,13 +181,21 @@ ml/purpose-classifier/venv/bin/python -u ml/purpose-classifier/train_mlx.py \ ml/purpose-classifier/outputs/purpose-lite-v1-boundary-teacher.pt \ --distillation-weight 0.9 --distillation-temperature 2 \ --distillation-selection-weight 0.5 --quantization-aware \ - --epochs 2 --early-stopping-patience 1 \ + --epochs 4 --early-stopping-patience 1 \ --learning-rate 1e-6 --warmup-ratio 0 --boundary-weight 1 \ --progress-steps 1 \ - --output-dir ml/purpose-classifier/outputs/purpose-lite-v1-distilled-qat-mlx \ + --output-dir ml/purpose-classifier/outputs/purpose-lite-v1-distilled-qat-mlx-4e \ --overwrite-output ``` +The full Metal run stopped after epoch three and selected epoch two at 94.75% fake-quant +validation accuracy. Its 23,148,500-byte int8-QDQ export scores **95.20% frozen +(892/937)**, 95.19% macro recall, 94.17% scored-hard accuracy, and 98.08% scorable +PyTorch↔ONNX agreement. Every purpose recall is above 91%, and the vague-abstention and +routing-tier-drift gates pass. This is the current accuracy-qualified shipping candidate; +latency and energy/residency still require measurement on the target Apple and Windows +accelerator runtimes. + For a wiring smoke test, use a small deterministic prefix: ```bash