{
  "datasets_json_loader": {
    "train": 1138,
    "validation": 126,
    "features": "{'id': Value('string'), 'group_id': Value('string'), 'grade': Value('string'), 'topic': Value('string'), 'skill': Value('string'), 'kind': Value('string'), 'cbse_outcomes': List(Value('string')), 'messages': List({'role': Value('string'), 'content': Value('string')}), 'response': {'answer': Value('string'), 'practice_question': Value('string'), 'practice_answer': Value('string'), 'new_words': List({'word': Value('string'), 'meaning': Value('string')}), 'encouragement': Value('string')}, 'quality': {'original_content': Value('bool'), 'vocabulary_warnings': List(Value('null')), 'teacher_reviewed': Value('bool')}}"
  },
  "original_colab_bundle_data_reproduction": {
    "train": {
      "byte_identical": true
    },
    "validation": {
      "byte_identical": true
    }
  },
  "tokenizer": {
    "loaded": true,
    "tokenizer_class": "PreTrainedTokenizerFast",
    "vocab_size": 128256,
    "chat_template_grades": {
      "nursery": {
        "tokens": 344,
        "non_thinking_marker_present": true
      },
      "lkg": {
        "tokens": 344,
        "non_thinking_marker_present": true
      },
      "ukg": {
        "tokens": 340,
        "non_thinking_marker_present": true
      },
      "class_1": {
        "tokens": 343,
        "non_thinking_marker_present": true
      },
      "class_2": {
        "tokens": 343,
        "non_thinking_marker_present": true
      },
      "class_3": {
        "tokens": 345,
        "non_thinking_marker_present": true
      },
      "class_4": {
        "tokens": 343,
        "non_thinking_marker_present": true
      },
      "class_5": {
        "tokens": 345,
        "non_thinking_marker_present": true
      }
    },
    "fix_mistral_regex": true
  },
  "architecture": {
    "loaded_config": "SmolLM3Config",
    "model_type": "smollm3"
  }
}