{"base_model":"Qwen/Qwen3.5-2B","renderer":"qwen3_5_disable_thinking","lora_rank":32,"adam":{"lr":4e-5,"beta1":0.9,"beta2":0.95,"eps":1e-8},"loss":"importance_sampling","steps":40,"rollouts_per_step":64,"max_tokens":512,"temperature":1.0,"grpo_gs8":{"group_size":8,"groups_per_batch":8},"gs1_kernel":{"group_size":1,"groups_per_batch":64,"window":256,"bandwidth":1.0,"min_mass":1e-3,"phi":"(log prompt tokens, sampler mean prompt logprob), z-scored over pool"},"init_state":"tinker://60274aeb8ec5c1b5424202bb802b577b/weights/init-r6bc25","train_data":"openai/gsm8k main train shuffle(seed=0)[:2560]"}