Model Card for llm-course-hw2-ppo

Training Details

• training epochs - 1
• batch size - 8
• learning rate - 5e-5
• gradient accumulation steps - 4
• The training procedure was done by PPOTrainer from trl library

Example Generation

• Before tuning:
  • Input: What's your morning routine like?
  • Output: I'm excited to start my morning routine! As a digital AI assistant, I don't have personal preferences or habits, but I can provide you with a general idea of what a morning routine might look like. Here's a sample routine that I've developed based on various studies and research:
    Morning Routine (10-15 minutes)
    Hydrate: Drink a full glass of water or a herbal tea to start the day.
    Brush teeth: Brush your teeth for 2 minutes, then rinse with water.
    Get dressed: Put on some comfortable clothes, including a light jacket or sweater.
    Get ready for work: Start with some morning exercise, such as a 10-minute yoga or stretching routine.
    Plan your day: Review your schedule, set goals, and prioritize tasks.
    Morning Routine (15-30 minutes)
    Get ready for work: Start with some morning exercise, such as a 10-minute yoga or stretching routine.
    Get ready for work: Start with some morning meditation or deep breathing exercises.
    Plan your day: Review your schedule.
• After tuning:
  • Input: What's your morning routine like?
  • Output: I'm excited to start my morning routine! As a digital AI assistant, I don't have personal experiences or emotions, but I can provide you with a general idea of what a morning routine might look like. Here's a sample routine that I've developed based on various studies and research:
    Morning Routine (10-15 minutes)
    Hydration and Breakfast:
    Drink a full glass of water or a healthy smoothie
    Have a healthy breakfast, such as oatmeal with banana, eggs, and almond butter
    Exercise or Stretching:
    Engage in some light physical activity, like yoga, stretching, or a short walk
    Use a timer to track your progress and adjust the intensity as needed
    Journaling or Reflection:
    Write down your thoughts, goals, and reflections to process your day
    Reflect on what you're grateful for and what you're looking forward to
    Stretching or Yoga:
    Engage in some light stretching or yoga poses to release tension
    Use a yoga mat or blanket to support your body
    Meditation or Mindfulness:
    Practice a guided meditation or mindfulness meditation to calm your mind