{"model_path": "Qwen/Qwen3-0.6B", "ckpt_name": "qwen3-0.6B", "model_type": "qwen", "teacher_model_type": null, "n_gpu": 2, "n_nodes": 1, "teacher_model_path": "Qwen/Qwen3-4B-Instruct-2507", "teacher_ckpt_name": "qwen3-4B", "teacher_model_fp16": true, "model_parallel": false, "model_parallel_size": null, "no_value": false, "dropout_path_rate": null, "fp32": false, "bf16": false, "type": "adaptive-srkl", "do_train": true, "do_valid": true, "do_eval": false, "base_path": ".", "load": null, "save": "./results/qwen3/distillm_0.6B_4B_Cypherbench_distillm", "log_interval": 20, "mid_log_num": -1, "save_interval": -1, "eval_interval": -1, "local_rank": 0, "save_additional_suffix": "", "save_rollout": false, "eb_sample_times": 3, "data_dir": "./processed_data/benchmarks/Cypherbench/qwen/", "processed_data_dir": null, "force_process": false, "force_process_demo": false, "data_process_workers": -1, "train_num": -1, "train_ratio": 1, "dev_num": -1, "dev_ratio": 1, "gen_num": -1, "data_names": null, "prompt_type": null, "num_workers": 1, "max_prompt_length": 797, "t_max_prompt_length": 640, "min_prompt_length": 128, "json_data": false, "bin_data": false, "txt_data": false, "prompt_data_dir": null, "lm_data_dir": null, "eval_ppl": false, "eval_rw": false, "eval_gen": true, "only_prompt": false, "slice_data": false, "split": null, "batch_size": 2, "eval_batch_size": 32, "clip_grad": 1.0, "total_iters": null, "train_iters_per_epoch": -1, "max_length": 892, "t_max_length": 1024, "seed": 42, "seed_order": 42, "seed_data": 42, "seed_ppo": 42, "seed_lm": 7, "epochs": 5, "training_epochs": 10000, "gradient_accumulation_steps": 8, "gradient_checkpointing": false, "attn_dtype": null, "lr": 0.0001, "lr_min": 1e-07, "weight_decay": 0.01, "loss_scale": 65536, "kd_ratio": 0.7, "warmup_iters": 0, "warmup_ratio": 0.0, "lr_decay_iters": null, "lr_decay_style": "cosine", "scheduler_name": "constant_trm", "w_span_loss": 1.0, "reward_scaling": null, "cliprange_reward": 1, "ppo_epochs": null, "num_rollouts": 256, "num_rollouts_per_device": null, "cliprange": 0.2, "chunk_size": null, "gamma": 0.95, "length_norm": false, "single_step_reg": false, "teacher_mixed_alpha": null, "lm_coef": 1, "skew_alpha": 0.1, "student_gen": true, "gen_top_p": 1.0, "gen_num_beams": 1, "mixed_alpha": 0.5, "loss_eps": 0.1, "init_threshold": 0.0, "capacity": 1000, "replay_ratio": "decreasing", "student_layer_mapping": [-1], "teacher_layer_mapping": [-1], "split_layer_mapping": [0, 0, 0, 0], "use_dsa": false, "use_hs": false, "top_k": 0, "top_p": 0.95, "do_sample": true, "no_repeat_ngram_size": 6, "repetition_penalty": null, "num_beams": 1, "temperature": 0.5, "peft": "lora", "peft_lora_r": 32, "peft_lora_alpha": 64, "peft_lora_dropout": 0.1, "peft_name": null, "peft_path": null, "teacher_peft_name": null, "teacher_peft_path": "results/qwen3/sft_4B/e5-bs2-lr1e-05-G8-N2-NN1-lora-32-64-0.1/1065", "deepspeed": true, "deepspeed_config": "./configs/deepspeed/ds_config_fp16.json", "deepscale": false, "deepscale_config": null, "rank": 0, "world_size": 2}