{
  "country": "Canada",
  "shuffle_seed": 0,
  "learning_rate": 1e-06,
  "tau": 0.7,
  "beta": 1.1,
  "batch_size": 8,
  "max_steps": 1024,
  "method": "filtered_weighted",
  "model_name": "OpenAssistant/reward-model-deberta-v3-base",
  "split_seed": 0,
  "model_seed": 0,
  "trainer_seed": 42,
  "trainer_data_seed": null
}