Qwen3-1.7B-ReMax-math-reasoning

This model is a fine-tuned version of Qwen3-1.7B using ReMax without KL penalty for mathematical reasoning.

Trained with PipelineRL.

Training Details

Datasets

Split	Datasets
Train	gsm8k_train, math_train
Test	gsm8k_test, math_500

RL Algorithm

Parameter	Value
Algorithm	ReMax
Advantage Baseline	Greedy-decoded response reward
Extra Inference	1 deterministic rollout per prompt
Group Structure	Not required
Policy Loss	ppo
KL Coefficient	0.0
Epsilon (clip)	0.2
Discount Factor (gamma)	1.0
Divide Advantage by Std	False
Filter Zero Advantage Groups	False
Rollouts per Problem	16

ReMax uses a greedy-decoded response's reward as the baseline for advantages.

Training Hyperparameters

Parameter	Value
Base Model	Qwen/Qwen3-1.7B
Learning Rate	1e-06
LR Scheduler	cosine
Warmup Steps	25
Max Training Steps	1500
Micro Batch Size	4
Gradient Accumulation	64
Effective Batch Size	256
Sequence Length	8192
Gradient Clipping	0.3
Weight Decay	0.01
Optimizer	adamw_torch
Precision	bf16
DeepSpeed	ZeRO Stage 3

Evaluation Results

Pass@k on math reasoning benchmarks (N=32 samples per problem, temperature=1.0):

Dataset	pass@1	pass@2	pass@4	pass@8	pass@16	pass@32
GSM8K (test)	81.09	86.82	90.59	92.95	94.35	95.22
MATH-500	71.04	78.56	84.33	88.57	91.54	93.40
Overall	78.32	84.55	88.87	91.74	93.58	94.72

GSM8K test: 1319 problems · MATH-500: 500 problems · Overall: 1819 problems (overall weighted by problem count).

Training Curves

W&B Run

Full training logs: https://wandb.ai/jaygala24-team/rl-post-training/runs/qwen3_1.7b_remax_3a1f_4xh100_214751_finetune_68632ef0

Usage

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("jaygala24/Qwen3-1.7B-ReMax-math-reasoning", revision="step-0200")  # optional branch, e.g. "step-0400"
tokenizer = AutoTokenizer.from_pretrained("jaygala24/Qwen3-1.7B-ReMax-math-reasoning", revision="step-0200")

prompt = "Please reason step by step, and put your final answer within \\boxed{}.\n\nWhat is the sum of 123 and 456?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

vLLM

from vllm import LLM, SamplingParams

llm = LLM(model="jaygala24/Qwen3-1.7B-ReMax-math-reasoning", revision="step-0200")  # optional branch, e.g. "step-0400"
sampling_params = SamplingParams(temperature=0.7, max_tokens=4096)

prompt = "Please reason step by step, and put your final answer within \boxed{}.

What is the sum of 123 and 456?"
outputs = llm.generate([prompt], sampling_params)
print(outputs[0].outputs[0].text)

Framework

• PipelineRL
• Transformers
• DeepSpeed (ZeRO Stage 3)