{"base_model":"Qwen/Qwen3.5-2B","lora_rank":32,"arm":"dppo_diag","loss":"dppo_binary_tv","delta":0.15,"clip_ratio_c":10.0,"ppo_eps_counterfactual":0.2, "optimizer":{"type":"adamw","learning_rate":2e-05,"beta1":0.9,"beta2":0.95,"eps":1e-08,"weight_decay":0.0,"grad_clip_norm":0.0}, "renderer":"qwen3_5_disable_thinking","temperature":1.0,"max_tokens":512,"groups":32,"group_size":8,"data_seed":0,"batch_index":0, "minibatches":8,"groups_per_minibatch":4,"epochs":2,"max_updates":16,"loss_normalization":"token sum (Spindle stock _loss convention)", "init_state_path":"tinker://21e32976f18f971463410adff4e364e4/weights/rx19badd842c_init","endpoint":"shared Spindle (TINKER_BASE_URL)", "sdk":{"tinker":"0.37.0","torch":"2.15.0"},"wall_cap_seconds":720,"n_eval":0}