52 lines
1.5 KiB
YAML
52 lines
1.5 KiB
YAML
|
model:
|
|||
|
|
name: "hfl/chinese-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: 0 # 0 for Windows (avoids multiprocessing issues); set to 4 on Linux
|
|||
|
|
|
|||
|
|
training:
|
|||
|
|
epochs: 10
|
|||
|
|
per_gpu_batch_size: 16 # single GPU: 16; 4 GPUs: use 32 (effective 128)
|
|||
|
|
gradient_accumulation_steps: 2 # effective_batch = 16 × 1 GPU × 2 = 32
|
|||
|
|
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: bf16; RTX 30xx/40xx: fp16; CPU-only: no
|
|||
|
|
seed: 42
|
|||
|
|
|
|||
|
|
loss_weights:
|
|||
|
|
binary: 1.0
|
|||
|
|
level: 1.0
|
|||
|
|
primary: 1.0
|
|||
|
|
fine: 1.0 # 下次训练建议提升到 2.0，配合 fine_training 选项
|
|||
|
|
|
|||
|
|
# Fine-grained label training options（下次训练时开启，当前 best.pt 不受影响）
|
|||
|
|
fine_training:
|
|||
|
|
use_pos_weight: false # 改为 true 开启 pos_weight（下次训练）
|
|||
|
|
risky_only: false # 改为 true 开启（下次训练）
|
|||
|
|
|
|||
|
|
evaluation:
|
|||
|
|
binary_threshold: 0.5
|
|||
|
|
fine_threshold: 0.4
|
|||
|
|
|
|||
|
|
logging:
|
|||
|
|
project: "CompanionGuard-RL"
|
|||
|
|
run_name: "detector-macbert-v1"
|
|||
|
|
use_wandb: false # set true if wandb is configured
|
|||
|
|
|
|||
|
|
output:
|
|||
|
|
checkpoint_dir: "checkpoints/detector"
|