Files
Video-Tree-TRM5/config/default.yaml
iomgaa 8958eee11b refactor: remove block-sequential gate path and gate_block knob (algo #6)
config/train_videomme.yaml 同时收录待入库的实验配置变更(run_id v2 /
concurrency 32 / batch_size 40)。tests/integration/test_v3_contract_e2e.py
的 run_id 断言按 Task 5 显式契约同步修正(原断言依赖旧隐式实例注入)。
2026-07-17 04:40:30 -04:00

98 lines
2.7 KiB
YAML

# config/default.yaml
# 科研实验配置默认值来源(会在实验中反复扫动/对比的参数)。
# 工程配置(少变、敏感)由 .env / pydantic-settings 管理,不在此文件。
# 优先级: CLI args > 此文件。CLI 仅用于单次临时覆盖。
# ── 建树模块 ──
tree:
max_paragraphs_per_l2: 5
l1_segment_duration: 600.0 # L1 段时长(秒)
l2_clip_duration: 60.0 # L2 clip 时长(秒)
l3_fps: 0.5 # L3 帧提取频率(帧/秒)
l2_representative_frames: 6 # L2 VLM 描述用的代表帧数
cache_dir: "cache/trees"
concurrency: 16 # asyncio Semaphore 上限
subtitle_inject: true # 建树时是否注入 SRT 字幕
srt_window_sec: 5.0 # 字幕匹配时间窗口(前后各 N 秒)
# ── Embedding ──
embed:
backend: "local"
model_name: "BAAI/bge-base-zh-v1.5"
embed_dim: 768
device: "cuda"
# ── Harness 自进化循环 ──
harness:
workspace_dir: "workspaces/default"
store_dir: store
mode: infer
concurrency: 24
max_steps: 40
skill_mode: auto
n_samples: 0
questions: "benchmarks/Video-MME"
skills_version: v1
prompts_version: v1
epochs: 1
# CE-Gate 参数
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_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
# 数据池
diag_size: 200
diag_correct_ratio: 0.5
val_size: 30
val_correct_ratio: 0.5
test_size: 60
# mini-batch
batch_size: 15
min_class_per_batch: 2
batch_correct_ratio: 0.5
momentum_samples: 20
eval_min_per_class: 2
trainable_min_units: 8
early_stop_patience: 8
use_slow_momentum: true
# 池构建策略
pool_split_mode: global # global | per_category
train_ratio: 0.667 # per_category 模式下 train/(train+val) 比例
test_questions: "benchmarks/Video-MME" # test 池的题目来源
# ── 出题管线 v2 ──
question_gen_v2:
family_ratios:
retrieval: 0.30
reasoning: 0.25
enumeration: 0.20
visual: 0.15
spatial: 0.10
gate:
blind_answer_model: "gpt-4.1-mini"
leak_test_model: "gpt-4.1-mini"
key_verify_model: "gpt-4.1-mini"
multi_true_model: "gpt-4.1-mini"
dedup_threshold: 0.85
retry_limit: 3
heavy_sample_rate: 0.15
heavy_agent_model: "gpt-4.1-mini"
output_dir: "store/questions/generated-v2"
per_type: 20 # 12 类 x 20 = 240 题(设计 §3 硬约束)
concurrency: 4
seed: 42