Files
Video-Tree-TRM5/config/question_gen_180_补.yaml
T
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

81 lines
1.9 KiB
YAML

# 补生 Video-MME 6 类缺失题型(180 题)
# 原 360 题中有 6 类错误类型已归档,此配置只生成缺失的 6 类。
# ── 建树模块 ──(与 question_gen_360.yaml 一致)
tree:
max_paragraphs_per_l2: 5
l1_segment_duration: 600.0
l2_clip_duration: 60.0
l3_fps: 0.5
l2_representative_frames: 6
cache_dir: "cache/trees"
concurrency: 16
subtitle_inject: true
srt_window_sec: 5.0
# ── Embedding ──
embed:
backend: "local"
model_name: "BAAI/bge-base-zh-v1.5"
embed_dim: 768
device: "cuda"
# ── Harness ──(占位,出题不使用)
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
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
edit_budget_start: 5
edit_budget_end: 2
skill_update_mode: patch
appendix_consolidate_threshold: 6
diag_size: 200
diag_correct_ratio: 0.5
val_size: 30
val_correct_ratio: 0.5
test_size: 60
batch_size: 15
min_class_per_batch: 2
batch_correct_ratio: 0.5
momentum_samples: 20
eval_min_per_class: 2
early_stop_patience: 8
use_slow_momentum: true
# ── 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
dedup_threshold: 0.85
retry_limit: 10
heavy_sample_rate: 0.15
output_dir: "store/questions/generated-v2-180补"
per_type: 30 # 6 类 x 30 = 180 题
concurrency: 24
seed: 43 # 不同于原始 seed=42,避免生成相同题目