A full-weight reinforcement-learning expert trained by Baseten on Spiral Matrix using GRPO with Adam. Traverse a matrix in spiral order. This repository contains the final inference checkpoint after 100 optimizer updates.
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0.49b07130b3fcd12f2d064bba7c43869543a0e7e7. The experiment used a frozen task bank and a completed-answer binary reward adapter derived from this environment; these results are not an official upstream benchmark score.ztbokdrf.| Checkpoint | Accuracy | Correct / scored completions | Truncation |
|---|---|---|---|
| Pinned base model, before environment training | 34.50% | 138 / 400 | 0.00% |
| Final expert, update 100 | 100.00% | 400 / 400 | 0.00% |
Accuracy improved by 65.50 percentage points from the pinned base model. Each evaluation uses 50 held-out tasks × 8 sampled completions = 400 scored completions. Accuracy is the mean binary correctness across all completions, not best-of-eight or pass-at-eight. Truncated responses remain in the denominator and count as failures. The reported endpoint is the final checkpoint, not an earlier peak.
The bank contains 400 training cases and 50 separate held-out validation cases. Validation uses a dedicated inference role every 10 optimizer updates with fixed seeds [17, 43, 101, 137, 211, 307, 401, 503]. All scheduled evaluations and final inference/full-state archival were verified against native receipts. The same validation bank was inspected during training; there was no separate final confirmation set. Results establish performance on held-out cases within this environment and do not establish cross-environment transfer or broad general reasoning improvement.
| Setting | Value |
|---|---|
| Training | Full-weight GRPO; Adam |
| Learning rate | Constant 1e-6 |
| Adam betas / weight decay | (0.9, 0.98) / 0.1 |
| Policy clip epsilon / upper epsilon | 0.2 / 0.28 |
| KL / entropy coefficients | 0.0 / 0.0 |
| Batch per optimizer update | 8 questions × 8 completions = 64 responses |
| Total consumed training responses | 6,400 |
| Precision | BF16 model training and sampling |
| Thinking | Enabled; reasoning_effort="medium" |
| Sampling | Temperature 1.0, top-p 0.95, top-k 20 |
| Maximum generated tokens | 16384 |
| Context limit used in this experiment | 32768 |
| Checkpoint / validation interval | Every 10 optimizer updates |
| Async consumption | Ordered batches; maximum completed-update lag of 1 |
For comparable text generation, use the supplied tokenizer and chat template, keep thinking enabled with reasoning_effort="medium", and retain the sampling and output limits above. The original runtime pinned Transformers 5.12.1; detailed runtime revisions are recorded in the provenance JSON. This expert was trained and evaluated on text inputs. Vision or video performance and retention of unrelated base-model capabilities were not evaluated.
The source inference snapshot is miles-qwen3.8-27b-ab4dbe7a18bf/run-ab4dbe7a18bf/training/eval-snapshots/step_99. It was emitted at optimizer update 100 and verified complete in durable platform storage. The native final evaluation completed at 2026-10-19T11:56:55.442848+00:00. This release contains inference weights and required inference assets; resumable optimizer state and raw training/evaluation traces remain in the experiment archives.
The final validation result was also verified in the original W&B run.
This is a specialized research checkpoint for text reasoning in the named environment. Its results depend on the frozen bank, prompt and grading contract, decoding settings, and token budget. Broader task transfer, production safety, multimodal behavior, and performance under different decoding settings have not been established by these experiments.
Apache-2.0, following the pinned base model. See the accompanying license and the pinned base-model card.
The plots below show the recorded training trajectory and verified validation results for this environment. Training uses a running average of 10 with the original series visible; validation is unsmoothed. No training, evaluation, or interpolation was performed to create these images.
Training metric: rollout/raw_reward against rollout/step. Validation metric: eval/validation against completed optimizer updates.
Both published experts contain 100 optimizer updates. Their training curves use the full native axis 0–99; validation includes every scheduled point from 0 through 100. Restored runs retain their original checkpoint ancestry and exclude abandoned branches.
The overlay compares these recorded trajectories; it does not establish an optimizer-only causal effect. See each model’s settings and limitations above.
Adam is blue; SGD is pink.
Chart provenance and settings. The original weight commit is a2baa1b7fd7fab95d589b47d182e2a10a04e18ce.
model-00004-of-00018.safetensors 4.0 GBmodel-00016-of-00018.safetensors 4.0 GBmodel-00006-of-00018.safetensors 4.0 GBmodel-00008-of-00018.safetensors 4.0 GBmodel-00010-of-00018.safetensors 4.0 GBmodel-00012-of-00018.safetensors 4.0 GBmodel-00014-of-00018.safetensors 4.0 GBmodel-00001-of-00018.safetensors 3.0 GBmodel-00002-of-00018.safetensors 3.0 GBmodel-00003-of-00018.safetensors 2.5 GBmodel-00018-of-00018.safetensors 2.5 GBmodel-00007-of-00018.safetensors 2.1 GBmodel-00009-of-00018.safetensors 2.1 GBmodel-00011-of-00018.safetensors 2.1 GBmodel-00013-of-00018.safetensors 2.1 GBmodel-00015-of-00018.safetensors 2.1 GBmodel-00017-of-00018.safetensors 2.1 GBmodel-00005-of-00018.safetensors 2.1 GBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo baseten/spiral-matrix-adam-qwen38_27b-expert ./model-folderQwen/Qwen3.8-27B