config:
  name: "path/to/sft_model"
  max_new_tokens: 300 # reasoning + answer token budget
  exploration_batchsize: 8  # number of questions per batch during rollout
  G: 6  # num responses per group
  temperature: 0.7
  batch_size: 16  # minibatch size during training
  gradient_accumulation_steps: 12
  learning_rate: 0.000001  # Advisable to keep this low, like 1e-6 or 1e-7
  top_p: 0.95
  buffer_size: 500