GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
baseten
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
baseten
Model Tree
Qwen/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
| Checkpoint | Accuracy | Correct / scored completions | Truncation |
|---|---|---|---|
| Pinned base model before environment training | 55.75% | 223 / 400 | 4.75% |
| Final expert, update 100 | 94.25% | 377 / 400 | 3.00% |
Accuracy improved by 38.50 percentage points. Each evaluation uses 50 held-out tasks × 8 sampled completions = 400 scored completions. Accuracy is the mean binary reward across all completions; truncated responses remain in the denominator and count as failures. The endpoint is the final checkpoint, not an earlier peak.
The frozen bank contains 400 training cases and 50 held-out validation cases. A dedicated inference role evaluates every 10 optimizer updates with fixed seeds [17, 43, 101, 137, 211, 307, 401, 503]. All 11 logical evaluations, final inference/full-state archives and raw completion coverage were verified. The same validation bank was inspected throughout training, with no separate final confirmation set. These results do not establish cross-environment transfer, broad reasoning gains, or replicated causal effects of the optimizer.
| Setting | Value |
|---|---|
| Training | Full-weight GRPO; SGD |
| Learning rate | Constant 0.1 |
| SGD momentum / weight decay | 0.0 / 0.0 |
| Policy clip epsilon / upper epsilon | 0.2 / 0.28 |
| KL / entropy coefficients | 0.0 / 0.0 |
| Batch per update | 8 questions × 8 completions = 64 responses |
| Retained optimizer budget | 100 updates; 6,400 training responses |
| 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 / context limit | 16384 / 32768 |
| Async consumption | Ordered batches; maximum completed-update lag 1 |
| Checkpoint / validation interval | Every 10 optimizer updates |
For comparable text generation, use the supplied tokenizer and chat template, keep thinking enabled with reasoning_effort="medium", and retain these sampling limits. The original runtime pinned Transformers 5.12.1. The experiment trained and evaluated text inputs; multimodal performance and retention of unrelated capabilities were not measured.
The published weights come from this completed100-update attempt; earlier failed or preempted fresh attempts are not added to its optimizer budget.
The total logical training budget remains 100 updates and 6,400 consumed responses. Native checkpoint receipts preserve model, optimizer and data provenance. Raw responses and detailed derived grader labels remain separate from the unchanged binary rewards.
The source inference snapshot is miles-rg-bitwise-arithmetic-sgd100-20261022-r08-a6a76f30f2c6/rg-bitwise-arithmetic-sgd100-20261022-r08-a6a76f30f2c6/training/eval-snapshots/step_99. It belongs to training job 32ko123 in project wx4x80q and is COMPLETE in durable platform storage. Its original final evaluation completed at 2026-10-23T01:30:19.953549+00:00.
The W&B summary observed at 2026-10-23T04:06:26.787159+00:00 still reports update 90 at 91.50%. Full history was not rescanned, so this is specifically a summary discrepancy. Existing-run correction writes are permission-blocked. The 94.25% at update 100 reported here comes from original native receipts and verified raw coverage.
Only the final post-trained inference weights and required tokenizer/configuration/chat-template assets are selected for publication. The export contract permits file repacking while requiring exact tensor-bit preservation, with separate per-tensor hash and remote-file verification before publication is declared complete. No numerical conversion, quantization, averaging or base-weight substitution is permitted. Resumable full-state checkpoints, including SGD state, FP32 master weights, scheduler, RNG and cursor, and raw traces remain in Baseten archives and owning experiment evidence.
This is a specialized research checkpoint for the named text environment. Performance depends on the frozen task bank, prompt/grading contract, sampling settings and token budget. Broader task transfer, production safety, multimodal behavior and different decoding settings were not evaluated.
Apache-2.0, following the pinned base model. See the accompanying license and 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 43f39c73561c834471d88db70ff6002d15cc2949.