# config/train_videomme.yaml # Video-MME 900 题自进化训练 —— 消费 video-split 冻结切分(global 三池) # # 数据来源: workspaces/video-split/pools.json(tier 感知 diag/val + val 功效修复) # 经 adhoc-baseline seed 携带进 workspace(WP2 接线)。 # 训练前置: .env REDIS_CACHE_TTL 须为正整数(WP4 fail-loud);见 # research-wiki/reviews/2026-07-16-preflight-final-review.md runbook。 harness: workspace_dir: "workspaces/train-videomme" store_dir: store mode: train run_id: train_videomme_v1 concurrency: 24 max_steps: 40 skill_mode: auto n_samples: 0 questions: "benchmarks/Video-MME" # gate 指纹依赖加载全 900 题 skills_version: v1 prompts_version: v1 epochs: 3 # CE-Gate 参数(沿用 default.yaml) gate_e_confirm: 20.0 gate_e_provisional: 3.0 gate_w_net_min: 2 gate_delta_min: 0.02 gate_lambda_dir: -0.642 gate_e_rollback: 10.0 gate_block: 8 gate_n_max: 40 gate_p_low: 0.05 gate_p_high: 0.95 gate_probe_quota: 0.2 gate_gamma_decay: 0.9 gate_cooldown_steps: 2 gate_guard_err: 0.10 # 进化参数 edit_budget_start: 5 edit_budget_end: 2 skill_update_mode: patch appendix_consolidate_threshold: 6 # 池配置 —— global 冻结切分(diag/val/test 尺寸由 pools.json 冻结,以下采样旋钮加载时忽略) pool_split_mode: global diag_size: 210 diag_correct_ratio: 0.5 val_size: 90 val_correct_ratio: 0.5 test_size: 600 test_questions: "benchmarks/Video-MME" # 可训练性预检(WP3):val 单元 < eval_min_per_class 或 非test单元 < trainable_min_units 的题型剔除 eval_min_per_class: 2 trainable_min_units: 8 # mini-batch batch_size: 10 min_class_per_batch: 2 batch_correct_ratio: 0.5 momentum_samples: 20 early_stop_patience: 2 # epoch 粒度(WP3):连续 2 epoch 无 best 刷新即停 use_slow_momentum: true run_holdout_eval: true # 逐 epoch test 四向评估(WP3 去重版:baseline 推导 + 版本备忘录) # 全 12 题型(不指定 task_types 子集,避免 I-4 语义偏差;微型类由预检自动剔除) embed: backend: "local" model_name: "BAAI/bge-base-zh-v1.5" embed_dim: 768 device: "cuda"