66 lines
1.5 KiB
YAML
66 lines
1.5 KiB
YAML
# 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
|
||
trainable_min_units: 8
|
||
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"
|