| # OpenSysOne handover |
|
|
| **Recorded state, 17 September 2026, 09:22 UTC:** training, final validation, |
| evaluation and profiling completed with exit 0. Training remains stopped; both |
| Spark GPUs were idle at completion. Preserve all selected and resumable artifacts. |
|
|
| The selected Qwen3-4B decision scorer retains Spark B step-1,500 weights, unchanged |
| at expanded branch step 0. It achieved **92.90%** accuracy on the original test |
| and **72.92%** on the Social IQA family holdout. The measured implementation is |
| slower than both pretrained inference baselines. See [RESULTS.md](RESULTS.md). |
|
|
| The recorded remaining services are the calibrated loopback API on **18081** and |
| the browser playground on **7466**. Process IDs, exact source revisions, checkpoint |
| hashes, run paths and inspect/stop/restart commands are preserved in the |
| [full operational handover](docs/operations/handover.md). Check those records and |
| the live process identity before acting; this document does not restart any job. |
|
|
| For a continuation, read [PLAN.md](PLAN.md) and [RESULTS.md](RESULTS.md), then the |
| [full handover](docs/operations/handover.md) and relevant infrastructure page under |
| `/home/andy/ai/opensysone/gx10-reference`. Keep the 16 GiB per-process allocation |
| cap and existing model/data/source provenance checks. Historical launch plans in |
| the archived documents are superseded by the completed state above. |
|
|
| - [Documentation index](docs/README.md) |
| - [Playground usage and controls](docs/usage/playground.md) |
| - [Fleet history and serving-pair restoration](docs/operations/fleet.md) |
| - [Hugging Face publication records and controls](docs/operations/huggingface.md) |
| - [Complete report, tables and charts](results/report.md) |
|
|
