{ "target_path": "./av-model", "nla_dir": ".", "backbone": { "path": "./av-model", "quantization": "nf4", "compute_dtype": "bfloat16", "double_quant": true, "device_map": "auto", "trust_remote_code": true, "attn_implementation": "eager" }, "surgery": { "av_lora_rank": 48, "av_lora_alpha": 96, "av_lora_dropout": 0.0, "av_num_slots": 8, "av_proj_hidden": 3072, "ar_lora_rank": 128, "ar_lora_alpha": 256, "ar_lora_dropout": 0.0, "ar_head_hidden": 4096, "ar_unfreeze_output_proj": false, "lora_target_modules": [ "q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj", "in_proj_qkv", "out_proj" ] }, "activation": { "layer": 18, "layers": [ 18 ], "normalize": "standardize", "clamp_sigma": 8.0, "pca_dim": 512 }, "extract": { "out_dir": "./calibration", "num_examples": 120000, "max_seq_len": 128, "positions_per_context": 5, "skip_first": 4, "batch_size": 6, "context_window": 128, "corpus_max_texts": 80000, "corpus_max_chars": 600, "corpus_min_chars": 24, "corpus_include_thinking": true, "corpus_include_prompts": true, "corpus_seed": 0, "corpus_english_only": true }, "train": { "out_dir": "./run", "dataset_dir": "./calibration", "epochs": 2, "max_steps": 3500, "batch_size": 2, "grad_accum": 8, "lr": 0.0003, "weight_decay": 0.0, "warmup_ratio": 0.03, "max_grad_norm": 1.0, "max_explanation_tokens": 50, "min_explanation_tokens": 12, "w_cosine": 0.0, "w_mse": 0.0, "w_ar_teacher": 1.0, "ar_short_frac": 0.0, "w_distill": 0.5, "w_distill_final": 0.2, "distill_anneal_frac": 0.4, "w_recon_reward": 0.0, "grad_decode": false, "gumbel_tau": 1.0, "grad_checkpointing": true, "optim_8bit": true, "save_every": 350, "eval_every": 350, "log_every": 25, "eval_examples": 64, "seed": 0, "resume": true, "teacher_path": null, "max_distill_tokens": 24, "rl_max_new_tokens": 32, "rl_lr": 2e-05, "rl_entropy_coef": 0.02, "w_ar_coadapt": 0.0 } }