GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
hbin0701
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
hbin0701
Model Tree
Qwen/Qwen3-1.7B
Input Modalities
Output Modalities
Supported Functionality
<rewind> is one added token (id 151669, not special, so it decodes as the text <rewind> and works as a stop
string). It sits in a spare embedding row. Its embedding was initialised to the mean of the embeddings of
"Wait", "Alternatively" and "Hmm". Embeddings are tied, so this sets its output logit row too.
Paragraphs are blocks split at blank lines (\n\n); pieces under 40 characters merge forward.
Sections: a paragraph starts a new section when fewer than 43% of its content words appeared in the previous 3 paragraphs, once the current section has at least 300 tokens. The count is causal: the section starts of a prefix are the section starts of the whole text up to that point.
Rewind: delete the last 4 sections of the thinking (the section in progress counts as one), append
[rewound]\n\n, and continue. Fired with 4 or fewer sections written, it erases everything (a restart).
System prompt used in training and in every eval:
You may write while reasoning. It erases the last part of your reasoning (about the last four steps) so you can continue from the earlier point where things were still on track. Use it only when you realize your reasoning has gone wrong and continuing will not lead to a correct answer; do not use it for routine double-checking. You can use it at most once per problem, and never after . After a rewind, [rewound] marks where the erased part was.
The user turn is the problem + \n\nPlease reason step by step, and put your final answer within \boxed{}., and
the assistant turn opens with <think>\n.
From Sangsang/rewind-run1-sft-data (146 rows of
each type, built from Qwen3-1.7B's own DAPO-Math solutions):
| row type | prompt → completion | used here |
|---|---|---|
trigger | reasoning up to a drop → <rewind> | dropped (no tag to copy) |
post_rewind | reasoning 4 sections before the drop + [rewound] → a correct continuation | 101 (the 45 whose rewind kept nothing, i.e. restarts, are dropped) |
negative | an on-track prefix → a correct continuation | 146 |
393 rows in total, with 3,091 positions targeted at P0 (10.6 per non-rewound row) and 80,795 targeted at 0.
For one row with completion tokens x₁…x_T (prompt = system + problem + prefix, masked):
text
L_row = −(1/T) · Σ_{t=1..T} log π(x_t | ctx_t) (completion-only next-token loss) + λ · (1/|S|) · Σ_{t∈S} BCE(p_t, y_t) (prior term)p_t = π(<rewind> | ctx_t) the softmax probability of the tag token at completion position tBCE(p,y) = −[ y·log p + (1−y)·log(1−p) ]λ = 1 (--prior_weight)Batch loss = (1/8) · Σ over the 8 rows of the global batch of L_row.S and the targets y_t (prior_targets in sft_train.py):
starts[5:], --prior_min_sections 5). A rewind fired there always keeps
something, so it is never a restart.\n\n), and at the first thinking
token of rows whose prefix is empty.post_rewind rows (the one rewind is already used).The BCE gradient on the tag's logit is p_t − y_t, so the term is minimised exactly at p_t = y_t (its floor at P0 = 0.025 is the entropy H(0.025) ≈ 0.117 nats). At a P0 position the next-token term also pushes p_t down (gradient p_t / T), which moves the optimum to P0 · T / (T + |S|) ≈ 0.975 · P0 on this data.
Optimisation: full fine-tuning, AdamW (β = 0.9 / 0.999, weight decay 0.01), lr 2e-6 with 8 warmup steps then cosine to 0, 2 epochs = 98 steps of 8 rows, grad clip 1.0, seed 42, fp32 master weights with bf16 compute, sequences up to 32,768 tokens, 2 × A100 (≈ 27 min, 10.1M tokens).
bash
torchrun --nproc_per_node 2 sft_train.py --model Qwen/Qwen3-1.7B --data sft.jsonl --out ckpt_wait --lr 2e-6 \ --epochs 2 --batch_size 8 --warmup_steps 8 --max_rewinds 1 --system_prompt on --rewind_unit section \ --rewind_sections 4 --rewind_mark --tag_token --tag_init Wait+Alternatively+Hmm --rewind_prior 0.025 \ --prior_on all --prior_min_sections 5 --prior_weight 1 --drop_restartsCalibration at the end of training (mean P(<rewind>) over the last batch):
| positions | target | reached |
|---|---|---|
| legal spots | 0.025 | 0.0020 |
| other paragraph starts | 0 | 0.00055 |
| first thinking token | 0 | 0.0 |
The target at legal spots was not reached. Over the 98 steps, P at legal spots wandered between 0.001 and 0.005. The model learned roughly one flat rate at every paragraph start and little about which spots are legal.
Fire test: 64 DAPO-Math problems × 4 samples, temperature 1.0, top-p 1.0, 16,384 new tokens, system prompt on,
thinking on. Each sample stops at its first <rewind>, and nothing is rewound. A second run blocks the tag
(logit ban).
| measure | value |
|---|---|
solutions that write <rewind> (before </think>) | 21.5% |
| fires per paragraph break generated | 0.0010 (the best flat rate for this data would be 0.00092) |
| fires at a paragraph break | 100% |
| fire position, tokens (p25 / median / p75) | 1,989 / 4,230 / 7,535 (median 9 sections) |
| fires that would be restarts (≤ 4 sections written) | 30.9% |
fires after </think> | 0% |
| accuracy of samples that never fired |
Use with a guard. Because the rate is flat across paragraph starts, about 31% of fires would be restarts. In the
accompanying RL code, --guard_tokens 1500 --guard_sections 5 blocks the tag until the solution has 1,500 tokens
and 5 sections. That makes a restart impossible: 0 restarts in 15 RL steps and in eval.
python
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("hbin0701/Qwen3-1.7B-rewind-sftv3-wait")model = AutoModelForCausalLM.from_pretrained("hbin0701/Qwen3-1.7B-rewind-sftv3-wait", torch_dtype="bfloat16")Generate with <rewind> as a stop string. On a stop, delete the last 4 sections of the thinking, append
[rewound]\n\n, and continue with the tag banned. rewind_common.apply_section_rewind and eval_rewind.py in the
repo implement exactly this. Without the system prompt, the model behaves close to the base model.
clean| the problem → a full correct solution |
| 146 |
| 69.2% |
| accuracy with the tag blocked | 64.1% |
lone < lines with the tag blocked | 0% |
| paragraphs starting with "Wait" (sampled / tag blocked) | 8.4% / 9.0% |
| fire rate on hard / easy problems (0–1 vs 3–4 of 4 right with the tag blocked) | 28.6% / 16.7% |