{"base_model":"Qwen/Qwen3.5-2B","renderer":"qwen3_5_disable_thinking","convo_prefix":"MathEnv.standard_fewshot_prefix","lora_rank":32,"optimizer":"adamw","adam":{"learning_rate":4e-05,"beta1":0.9,"beta2":0.95,"eps":1e-08,"weight_decay":0.0,"grad_clip_norm":0.0},"loss_fn":"importance_sampling","steps":40,"rollouts_per_step":64,"max_tokens":512,"temperature":1.0,"train_data":"openai/gsm8k main train shuffle(seed=0), first 2560","arms":{"grpo_gs8":{"group_size":8,"groups_per_batch":8,"advantage":"stock cookbook group mean"},"gs1_kernel":{"group_size":1,"groups_per_batch":64,"advantage":"r_i - kernel baseline","window":256,"bandwidth":1.0,"min_mass":0.001,"phi":"(log prompt tokens, mean sampler prompt-token logprob), z-scored over window"}},"eval":{"split":"openai/gsm8k main test","n":1319,"temperature":0,"max_tokens":512}}