52 lines
1.1 KiB
YAML
52 lines
1.1 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
|
|||
|
|
ablation_mode: "response_only" # 消融：仅 Response 流，persona/context 均置空
|
|||
|
|
|
|||
|
|
training:
|
|||
|
|
epochs: 10
|
|||
|
|
per_gpu_batch_size: 16
|
|||
|
|
gradient_accumulation_steps: 2
|
|||
|
|
lr: 2e-5
|
|||
|
|
warmup_steps: 100
|
|||
|
|
weight_decay: 0.01
|
|||
|
|
gradient_clip: 1.0
|
|||
|
|
eval_steps: 100
|
|||
|
|
mixed_precision: "bf16"
|
|||
|
|
seed: 42
|
|||
|
|
|
|||
|
|
loss_weights:
|
|||
|
|
binary: 1.0
|
|||
|
|
level: 1.0
|
|||
|
|
primary: 1.0
|
|||
|
|
fine: 2.0
|
|||
|
|
|
|||
|
|
fine_training:
|
|||
|
|
use_pos_weight: true
|
|||
|
|
risky_only: true
|
|||
|
|
|
|||
|
|
evaluation:
|
|||
|
|
binary_threshold: 0.5
|
|||
|
|
fine_threshold: 0.4
|
|||
|
|
|
|||
|
|
logging:
|
|||
|
|
project: "CompanionGuard-RL"
|
|||
|
|
run_name: "detector-abl-response-only"
|
|||
|
|
use_wandb: false
|
|||
|
|
|
|||
|
|
output:
|
|||
|
|
checkpoint_dir: "checkpoints/detector_abl_response_only"
|