chore: snapshot in-progress question-gen work before preflight fixes
This commit is contained in:
@@ -0,0 +1,81 @@
|
||||
# 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_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
|
||||
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
|
||||
@@ -0,0 +1,87 @@
|
||||
# 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_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
|
||||
# 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
|
||||
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-v2-360"
|
||||
per_type: 30 # 12 类 x 30 = 360 题
|
||||
concurrency: 24
|
||||
seed: 42
|
||||
@@ -0,0 +1,64 @@
|
||||
# config/train_ar30.yaml
|
||||
# Action Recognition 训练 — 基于 SubPattern 靶向生成的 30 题
|
||||
# 对比基线: v2-360 的 AR 题（100% 单帧，训练无效）
|
||||
# 本次: AR30 题（6 种失败子模式靶向，跨段时序）
|
||||
|
||||
harness:
|
||||
workspace_dir: "workspaces/train-ar30"
|
||||
store_dir: store
|
||||
mode: train
|
||||
run_id: train_ar30_v1
|
||||
concurrency: 24
|
||||
max_steps: 40
|
||||
skill_mode: auto
|
||||
n_samples: 0
|
||||
questions: "generated-ar30"
|
||||
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 — per_category 单题型
|
||||
pool_split_mode: per_category
|
||||
task_types:
|
||||
- "Action Recognition"
|
||||
train_ratio: 0.667
|
||||
test_questions: "benchmarks/Video-MME"
|
||||
run_holdout_eval: false
|
||||
# mini-batch
|
||||
batch_size: 10
|
||||
min_class_per_batch: 2
|
||||
batch_correct_ratio: 0.5
|
||||
momentum_samples: 20
|
||||
eval_min_per_class: 2
|
||||
early_stop_patience: 4
|
||||
test_size: 63
|
||||
diag_size: 20
|
||||
diag_correct_ratio: 0.5
|
||||
val_size: 10
|
||||
val_correct_ratio: 0.5
|
||||
use_slow_momentum: true
|
||||
|
||||
embed:
|
||||
backend: "local"
|
||||
model_name: "BAAI/bge-base-zh-v1.5"
|
||||
embed_dim: 768
|
||||
device: "cuda"
|
||||
+12
-4
@@ -14,10 +14,18 @@ video_split:
|
||||
val_wrong_min: 20 # validation 池最少错题数（McNemar 检验功效阈 ≈ 20，低于则信号不足）
|
||||
val_ratio: 0.3 # validation 占 trainval 视频组总数的比例
|
||||
seed: 7 # 贪心选择器预洗牌 + 视频组题级切分种子（打破等增益 / 等槽平局）
|
||||
floor_k: # 各高信号 task_type 的 T2 defect 下限（硬约束）—— 占位，标定后替换
|
||||
Counting Problem: 3 # 取克制值 min(诊断可用 defect 数, 3)，避免把信号全抽进 trainval
|
||||
Object Reasoning: 3
|
||||
Action Reasoning: 3
|
||||
floor_k: # 各 task_type 的 T2 defect 下限（硬约束）—— 均衡覆盖全 11 类，标定于 1cb1c203 真实 T2 分布
|
||||
Object Reasoning: 5 # T2=25
|
||||
Information Synopsis: 5 # T2=13
|
||||
Action Reasoning: 5 # T2=11
|
||||
Counting Problem: 5 # T2=10
|
||||
Temporal Reasoning: 2 # T2=5
|
||||
Object Recognition: 2 # T2=5
|
||||
Action Recognition: 2 # T2=5
|
||||
Attribute Perception: 1 # T2=3
|
||||
Temporal Perception: 1 # T2=2
|
||||
OCR Problems: 1 # T2=2
|
||||
Spatial Perception: 1 # T2=1
|
||||
|
||||
diag: # 诊断口径指纹三分量（隔离不同诊断配置的信号，参与主键）
|
||||
prompt_version: diagnose_v1 # 诊断 prompt 版本标识（换 prompt 即换指纹，旧记录不被覆盖）
|
||||
|
||||
Reference in New Issue
Block a user