{ "args": { "train": "dev/splits_v2/train.jsonl", "select": "dev/splits_v2/selection.jsonl", "out": "release/lora-v2", "model_name": "Qwen/Qwen3.5-4B", "rank": 16, "alpha": 32, "lora_dropout": 0.05, "lr": 0.0001, "weight_decay": 0.01, "epochs": 2, "accum": 8, "fusion": 0.5, "ordinal_w": 0.5, "perm_w": 0.5, "perm_p": 0.5, "opaque_p": 0.5, "eval_every": 400, "patience": 3, "max_select": 400, "seed": 0 }, "n_train": 2150, "n_select": 161, "best_selection_loss": 0.8873302168802816, "best_step": 250, "log": [ { "step": 0, "seen": 0, "loss": 1.336758746236262, "acc": 0.7080745341614907, "by_family": { "adequacy": "7/10", "ambiguous": "7/7", "policy": "11/13", "probability": "29/60", "routing": "60/71" } }, { "step": 50, "seen": 400, "loss": 1.0610499146397323, "acc": 0.8260869565217391, "by_family": { "adequacy": "6/10", "ambiguous": "7/7", "policy": "8/13", "probability": "47/60", "routing": "65/71" } }, { "step": 100, "seen": 800, "loss": 1.031379698107586, "acc": 0.906832298136646, "by_family": { "adequacy": "8/10", "ambiguous": "7/7", "policy": "9/13", "probability": "55/60", "routing": "67/71" } }, { "step": 150, "seen": 1200, "loss": 0.9625220286051789, "acc": 0.8757763975155279, "by_family": { "adequacy": "6/10", "ambiguous": "6/7", "policy": "10/13", "probability": "52/60", "routing": "67/71" } }, { "step": 200, "seen": 1600, "loss": 0.9321816444499288, "acc": 0.9316770186335404, "by_family": { "adequacy": "9/10", "ambiguous": "6/7", "policy": "10/13", "probability": "60/60", "routing": "65/71" } }, { "step": 250, "seen": 2000, "loss": 0.8873302168802816, "acc": 0.9130434782608695, "by_family": { "adequacy": "7/10", "ambiguous": "6/7", "policy": "8/13", "probability": "58/60", "routing": "68/71" } }, { "step": 301, "seen": 2406, "loss": 0.9988113209218529, "acc": 0.9130434782608695, "by_family": { "adequacy": "6/10", "ambiguous": "6/7", "policy": "11/13", "probability": "58/60", "routing": "66/71" } }, { "step": 351, "seen": 2806, "loss": 1.0362505128805466, "acc": 0.9254658385093167, "by_family": { "adequacy": "7/10", "ambiguous": "6/7", "policy": "10/13", "probability": "58/60", "routing": "68/71" } }, { "step": 401, "seen": 3206, "loss": 0.990789322077885, "acc": 0.9192546583850931, "by_family": { "adequacy": "7/10", "ambiguous": "6/7", "policy": "9/13", "probability": "58/60", "routing": "68/71" } } ], "targets": [ "q_proj", "k_proj", "v_proj", "o_proj", "in_proj_qkv", "in_proj_z", "out_proj", "gate_proj", "up_proj", "down_proj" ] }