evaluation_summary.json

{
  "selection_criterion": "highest eval_accuracy among workspace checkpoints",
  "eval_accuracy_benchmark": "text_classification",
  "selected_checkpoint": "checkpoints/step_1000",
  "eval_accuracy": 0.828,
  "score_decimal_places": 3,
  "benchmark_scores": {
    "math_reasoning": 0.55,
    "logical_reasoning": 0.819,
    "common_sense": 0.736,
    "reading_comprehension": 0.7,
    "question_answering": 0.607,
    "text_classification": 0.828,
    "sentiment_analysis": 0.792,
    "code_generation": 0.65,
    "creative_writing": 0.61,
    "dialogue_generation": 0.644,
    "summarization": 0.767,
    "translation": 0.804,
    "knowledge_retrieval": 0.676,
    "instruction_following": 0.758,
    "safety_evaluation": 0.739
  }
}