zhangsiyuan
bd1f51c496
Merged code repo (CompanionGuard-RL) into single project-level git. Reorganized root: docs/, reference/, experiments/, tmp/active|archives/. Gitignored: data/, checkpoints/, .venv, experiment logs, tmp/archives. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
50 lines
936 B
YAML
50 lines
936 B
YAML
detector:
|
|
checkpoint: "checkpoints/detector/best.pt"
|
|
# Server 2 path — update this when running on server 2
|
|
model_name: "/root/siton-data-740d234e02d749f08fe5347b0c74c49f/zsy/macbert-large"
|
|
hidden_size: 1024
|
|
|
|
agent:
|
|
state_hidden: 256
|
|
dropout: 0.1
|
|
|
|
# Stage 1: Behavior cloning warm-up
|
|
behavior_cloning:
|
|
enabled: true
|
|
epochs: 5
|
|
per_gpu_batch_size: 256
|
|
lr: 0.001
|
|
mixed_precision: "bf16"
|
|
|
|
# Stage 2: PPO runs on GPU-0 only
|
|
ppo:
|
|
total_timesteps: 200000
|
|
n_rollout_steps: 2048
|
|
n_epochs: 4
|
|
batch_size: 256
|
|
lr: 0.0003
|
|
clip_eps: 0.2
|
|
entropy_coef: 0.01
|
|
value_coef: 0.5
|
|
max_grad_norm: 0.5
|
|
gamma: 0.99
|
|
gae_lambda: 0.95
|
|
|
|
environment:
|
|
max_turns: 20
|
|
|
|
evaluation:
|
|
binary_threshold: 0.5
|
|
|
|
preprocessing:
|
|
per_gpu_batch_size: 64
|
|
|
|
logging:
|
|
project: "CompanionGuard-RL"
|
|
run_name: "intervention-v5-1gpu"
|
|
use_wandb: false
|
|
|
|
output:
|
|
checkpoint_dir: "checkpoints/intervention"
|
|
save_interval: 10000
|