{"base_model":"Qwen/Qwen3.5-2B","lora_rank":32,"renderer":"qwen3_5_disable_thinking","optimizer":{"type":"adamw","lr":4e-05,"beta1":0.9,"beta2":0.95,"eps":1e-08},"loss_fn":"importance_sampling","steps":40,"rollouts_per_step":64,"max_tokens":512,"temperature":1.0,"arms":{"grpo_gs8":{"group_size":8,"groups":8},"gs1_kernel":{"group_size":1,"groups":64,"bandwidth":1.0,"window":256,"min_mass":0.001}},"init_checkpoint":"tinker://97af5cc4420906ad0572b9a4b349d326/weights/rx-gs1-init","train_prompts":"openai/gsm8k main train shuffled seed 0, consumed sequentially","eval":"openai/gsm8k main test 1319 greedy"}