Course: reinforcement-fine-tuning-llms-grpo

[Dev Only] Debug Info

tRPC Context Version:

{
  "courseVersionId": null
}

Course Data (getCourseBySlug):

{
  "courseId": 1058,
  "name": "Reinforcement Fine-Tuning LLMs With GRPO",
  "slug": "reinforcement-fine-tuning-llms-grpo",
  "type": "short_course",
  "progress": -1,
  "maintenanceMode": false,
  "releasedAt": "2025-05-21T08:00:00+00:00",
  "nextCourseSlug": null,
  "wpData": {
    "courseName": "Reinforcement Fine-Tuning LLMs with GRPO",
    "courseDescription": "Improve LLM reasoning with reinforcement fine-tuning and reward functions.",
    "coursePartner": [
      {
        "title": "Predibase",
        "logo": "https://home-wordpress.deeplearning.ai/wp-content/uploads/2025/05/QUvd03Ad_400x400.png"
      }
    ],
    "courseTopic": [
      "Evaluation and Monitoring",
      "Fine-Tuning",
      "GenAI Applications",
      "LLMOps",
      "LLM Serving",
      "Machine Learning",
      "Prompt Engineering",
      "Supervised Learning",
      "Transformers"
    ],
    "courseLevel": "Intermediate",
    "courseDuration": null,
    "marketingSlug": "reinforcement-fine-tuning-llms-grpo",
    "videoThumbnail": "https://home-wordpress.deeplearning.ai/wp-content/uploads/2025/05/1058_reinforcement-fine-tuning-llms-grpo.jpg"
  },
  "certProgress": 0,
  "accomplishmentProgress": 0,
  "lessons": {
    "sjbja": {
      "index": 1,
      "slug": "sjbja",
      "name": "Introduction",
      "type": "video",
      "videoId": 873,
      "time": 236,
      "programId": null,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "eklye": {
      "index": 2,
      "slug": "eklye",
      "name": "Introduction to reinforcement learning",
      "type": "video",
      "videoId": 874,
      "time": 467,
      "programId": null,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "r3p2x": {
      "index": 3,
      "slug": "r3p2x",
      "name": "Benefits of reinforcement finetuning",
      "type": "video",
      "videoId": 875,
      "time": 252,
      "programId": null,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "bxwwv": {
      "index": 4,
      "slug": "bxwwv",
      "name": "Can a large language model master Wordle",
      "type": "video_notebook",
      "videoId": 876,
      "time": 658,
      "programId": 24008,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "e5esw": {
      "index": 5,
      "slug": "e5esw",
      "name": "Reward functions",
      "type": "video_notebook",
      "videoId": 877,
      "time": 604,
      "programId": 24009,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "ub5r8": {
      "index": 6,
      "slug": "ub5r8",
      "name": "Reward functions with LLM as a judge",
      "type": "video_notebook",
      "videoId": 878,
      "time": 756,
      "programId": 24010,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "xxwlq": {
      "index": 7,
      "slug": "xxwlq",
      "name": "Reward hacking",
      "type": "video_notebook",
      "videoId": 879,
      "time": 420,
      "programId": 24011,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "aifo6": {
      "index": 8,
      "slug": "aifo6",
      "name": "Calculating loss in GRPO",
      "type": "video_notebook",
      "videoId": 880,
      "time": 1087,
      "programId": 24012,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "xfrzl": {
      "index": 9,
      "slug": "xfrzl",
      "name": "Putting it all together: Training Wordle",
      "type": "video_notebook",
      "videoId": 881,
      "time": 485,
      "programId": 24013,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "lo7ww": {
      "index": 10,
      "slug": "lo7ww",
      "name": "Conclusion",
      "type": "video",
      "videoId": 872,
      "time": 52,
      "programId": null,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "n4uo6": {
      "index": 11,
      "slug": "n4uo6",
      "name": "Quiz",
      "type": "quiz",
      "videoId": null,
      "time": 0,
      "programId": null,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": "2632991FEEB8452D82EB5C7B31",
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "locked",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": false,
        "saveNotebookCustomjsEnabled": false
      }
    },
    "ymyet": {
      "index": 12,
      "slug": "ymyet",
      "name": "Appendix – Tips, Help, and Download",
      "type": "notebook",
      "videoId": null,
      "time": 0,
      "programId": 24014,
      "chatbotId": null,
      "iframeUrl": null,
      "quizId": null,
      "progress": 0,
      "readingMaterialId": null,
      "accessControl": "full",
      "requiredUserTier": "pro",
      "features": {
        "saveNotebookToolbar": true,
        "saveNotebookCustomjsEnabled": true
      }
    }
  },
  "subtopics": {},
  "listing": [
    {
      "timeFrame": null,
      "moduleLabel": "Module 1",
      "name": null,
      "content": [
        {
          "key": "sjbja",
          "type": "lesson"
        },
        {
          "key": "eklye",
          "type": "lesson"
        },
        {
          "key": "r3p2x",
          "type": "lesson"
        },
        {
          "key": "bxwwv",
          "type": "lesson"
        },
        {
          "key": "e5esw",
          "type": "lesson"
        },
        {
          "key": "ub5r8",
          "type": "lesson"
        },
        {
          "key": "xxwlq",
          "type": "lesson"
        },
        {
          "key": "aifo6",
          "type": "lesson"
        },
        {
          "key": "xfrzl",
          "type": "lesson"
        },
        {
          "key": "lo7ww",
          "type": "lesson"
        },
        {
          "key": "n4uo6",
          "type": "lesson"
        },
        {
          "key": "ymyet",
          "type": "lesson"
        }
      ],
      "progress": 0
    }
  ],
  "totalDurationSeconds": 5017,
  "lastAccessTime": null,
  "reviewsCnt": 0,
  "activeVersionIds": []
}