# Environment configuration
env:
  group_size: 4
  max_batches_offpolicy: 3
  tokenizer_name: "Qwen/Qwen2.5-1.5B-Instruct"
  use_wandb: true
  rollout_server_url: "http://localhost:8000"
  wandb_name: "example_env"
  ensure_scores_are_not_same: true
  data_path_to_save_groups: null
  include_messages: true # if data_path_to_save_groups is set this will add the messages to the saved .jsonl

# OpenAI server configurations
openai:
  - model_name: "Qwen/Qwen2.5-1.5B-Instruct"
    base_url: "http://localhost:9001/v1"
    api_key: "x"
    weight: 1.0

slurm: false
testing: false