zhangsiyuan
52ba43f08d
- Module C: BC+PPO training v5/v6 done; eval results in experiments/eval_intervention_v{5,6}.json
- Reward: v5 label-aligned constrained reward (code/src/rl/reward.py)
- Ablations: Module B (history_r, response_only, full) + Module C (wo_category_reward)
- SOTA baselines: WildGuard and ShieldGemma2b eval scripts and results
- Paper: update sections 05–08 (Module B/C description, experiments table, discussion)
- Docs: add record.md (change log), update state.md and exp.md; retire change.md
- Tools: add html-to-ppt utilities and run_shieldgemma2b.sh
- Configs: add ablation YAML configs for Module B and C
- Cleanup: remove stale reference/ PNG screenshots
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
55 lines
1.7 KiB
YAML
55 lines
1.7 KiB
YAML
model:
|
||
name: "/root/siton-data-2849d4ce327c4ccfb233ce33868fe7fe/zsy/macbert-large"
|
||
hidden_size: 1024
|
||
num_heads: 8
|
||
dropout: 0.1
|
||
use_lora: false
|
||
|
||
data:
|
||
train_path: "data/processed/CompanionRisk-Bench/train.jsonl"
|
||
val_path: "data/processed/CompanionRisk-Bench/dev.jsonl"
|
||
test_path: "data/processed/CompanionRisk-Bench/test.jsonl"
|
||
max_persona_len: 128
|
||
max_context_len: 512
|
||
max_response_len: 256
|
||
max_history_turns: 5
|
||
num_workers: 4 # Linux server: 4 workers; Windows: use 0
|
||
|
||
training:
|
||
epochs: 10
|
||
per_gpu_batch_size: 16 # 4 GPUs × 16 × accum 2 = effective batch 128
|
||
gradient_accumulation_steps: 2
|
||
lr: 2e-5
|
||
warmup_steps: 100
|
||
weight_decay: 0.01
|
||
gradient_clip: 1.0
|
||
eval_steps: 100 # global steps between validation runs
|
||
mixed_precision: "bf16" # RTX 5090 native bf16
|
||
seed: 42
|
||
|
||
loss_weights:
|
||
binary: 1.0
|
||
level: 1.0
|
||
primary: 1.0
|
||
fine: 2.0 # ↑ 2.0: 加强细粒度标签损失权重（配合 fine_training 开启）
|
||
|
||
# Fine-grained label training options（下次训练时开启，当前 best.pt 不受影响）
|
||
# 两项均开启可显著改善 fine_macro_f1：
|
||
# use_pos_weight: 对 Romanticization/CoRumination 等稀有标签设置 ~25 倍正样本权重
|
||
# risky_only: 只在 y_risk=1 的样本上计算 fine loss，避免 safe 样本教模型预测全负
|
||
fine_training:
|
||
use_pos_weight: true # ✓ 开启：对稀有 fine 标签设置 pos_weight（max 30）
|
||
risky_only: true # ✓ 开启：只在 y_risk=1 样本上计算 fine loss
|
||
|
||
evaluation:
|
||
binary_threshold: 0.5
|
||
fine_threshold: 0.4
|
||
|
||
logging:
|
||
project: "CompanionGuard-RL"
|
||
run_name: "detector-macbert-4gpu"
|
||
use_wandb: false
|
||
|
||
output:
|
||
checkpoint_dir: "checkpoints/detector"
|