GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
XudongZhu
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
XudongZhu
Model Tree
Qwen/Qwen3-1.7B-Base
Input Modalities
Output Modalities
Supported Functionality
Each checkpoint answers each question once (temperature 0.6, top-p 0.95, up to 15,360 tokens, seed 0; vLLM in BF16), with the prompt format below:
\boxed{}, and the answer counts as right when that letter is right.Accuracy:
| Step | ID | MATH-500 | MMLU-Pro |
|---|---|---|---|
| 0 (base) | 0.220 | 0.562 | 0.218 |
| 10 | 0.248 | 0.590 | 0.240 |
| 25 | 0.240 | 0.614 | 0.241 |
| 50 | 0.246 | 0.620 | 0.257 |
| 100 | 0.266 | 0.640 | 0.292 |
| 150 | 0.302 | 0.632 | 0.304 |
| 200 | 0.288 | 0.664 | 0.318 |
| 250 | 0.290 | 0.638 | 0.316 |
| 300 | 0.312 | 0.652 | 0.344 |
Each checkpoint is a branch named after its step: step1 to step50, then step60, step70, …, step300. main holds the last one (step 300). Step 0 is the base model itself.
python
from transformers import AutoModelForCausalLM, AutoTokenizer repo = "XudongZhu/Qwen3-1.7B-Base-SFT-OnPolicy"model = AutoModelForCausalLM.from_pretrained(repo, revision="step100")tokenizer = AutoTokenizer.from_pretrained(repo, revision="step100")Without revision, you get step 300. All branches: huggingface_hub.list_repo_refs(repo).branches.
The user turn is the problem, a blank line, and Please reason step by step, and put your final answer within \boxed{}. There is no system prompt; tokenizer.apply_chat_template builds this:
text
<|im_start|>user{problem} Please reason step by step, and put your final answer within \boxed{}.<|im_end|><|im_start|>assistantData. From the default split of OpenR1-Math-220k (93,733 problems):
The run trains on these 38,400 problems in this order, once. The length limit counts the R1 answer even in this run, so that both runs see the same problems.
One step. For each of 128 problems, the current model samples 8 answers (temperature 1.0, top-p 1.0, up to 15,360 tokens). math-verify compares the last 2,000 characters of each answer with the reference answer. For each problem, one correct answer is kept at random; a problem with no correct answer is skipped in this step. One optimizer step then minimizes the SFT loss on the kept answers: the mean of −log p over their tokens, without the prompt.
| Hyperparameter | Value |
|---|---|
| Optimizer | AdamW (β = 0.9, 0.999), weight decay 0, gradient clipping 1.0 |
| Learning rate | 1e-6, constant, no warmup |
| Batch | 128 problems per step, one optimizer step |
| Sampling | 8 answers per problem, temperature 1.0, top-p 1.0 |
| Length | prompt ≤ 1,024 tokens, answer ≤ 15,360 tokens |
| Steps | 300, one pass over the data |
| Precision | FP32 weights; BF16 compute and FP32 gradient reduction (FSDP mixed precision); BF16 sampling |
| Seeds | sampling 42; picking the kept answer 0 |
For research on training dynamics: compare weights or behavior across checkpoints, and against the off-policy twin. The run trains only on English math problems, with no instruction tuning or safety training beyond the base model; its answers are long chains of reasoning. Each accuracy above comes from one sample per question, so small differences between steps are not reliable.
from transformers import AutoModelForCausalLM, AutoTokenizer repo = "XudongZhu/Qwen3-1.7B-Base-SFT-OnPolicy"model = AutoModelForCausalLM.from_pretrained(repo, revision="step100")tokenizer = AutoTokenizer.from_pretrained(repo, revision="step100")<|im_start|>user{problem}Please reason step by step, and put your final answer within \boxed{}.<|im_end|><|im_start|>assistant