checkpoint,step,overall_score,is_selected,math_reasoning,code_generation,text_classification,sentiment_analysis,question_answering,logical_reasoning,common_sense,reading_comprehension,dialogue_generation,summarization,translation,knowledge_retrieval,creative_writing,instruction_following,safety_evaluation step_100,100,0.688,false,0.514,0.620,0.805,0.779,0.586,0.793,0.719,0.674,0.625,0.748,0.785,0.654,0.591,0.737,0.721 step_200,200,0.691,false,0.518,0.623,0.808,0.781,0.589,0.797,0.722,0.677,0.628,0.751,0.788,0.657,0.594,0.740,0.724 step_300,300,0.694,false,0.522,0.626,0.811,0.783,0.592,0.801,0.724,0.680,0.630,0.753,0.791,0.660,0.596,0.743,0.727 step_400,400,0.697,false,0.526,0.629,0.814,0.785,0.595,0.805,0.727,0.683,0.633,0.756,0.794,0.663,0.599,0.746,0.730 step_500,500,0.700,false,0.530,0.632,0.816,0.787,0.598,0.808,0.729,0.686,0.636,0.758,0.796,0.666,0.601,0.749,0.732 step_600,600,0.702,false,0.534,0.636,0.819,0.789,0.601,0.811,0.731,0.690,0.638,0.761,0.798,0.669,0.604,0.752,0.734 step_700,700,0.705,false,0.538,0.639,0.821,0.790,0.603,0.814,0.733,0.693,0.640,0.763,0.800,0.671,0.606,0.754,0.736 step_800,800,0.707,false,0.542,0.643,0.824,0.791,0.605,0.816,0.735,0.696,0.642,0.765,0.802,0.673,0.608,0.756,0.737 step_900,900,0.709,false,0.546,0.646,0.826,0.792,0.606,0.818,0.736,0.698,0.643,0.766,0.803,0.675,0.609,0.757,0.738 step_1000,1000,0.710,true,0.550,0.650,0.828,0.792,0.607,0.819,0.736,0.700,0.644,0.767,0.804,0.676,0.610,0.758,0.739