55 lines
1.7 KiB
YAML
55 lines
1.7 KiB
YAML
|
model:
|
|||
|
|
name: "/root/siton-data-740d234e02d749f08fe5347b0c74c49f/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"
|