step,critic_score_mean,val_math_dapo_acc_mean_at_1 1,0.17138671875, 2,0.193359375, 3,0.17919921875, 4,0.20849609375, 5,0.17236328125, 6,0.18994140625, 7,0.1748046875, 8,0.18994140625, 9,0.19091796875, 10,0.18212890625,0.16666666666666666 11,0.20166015625, 12,0.24658203125, 13,0.2158203125, 14,0.20166015625, 15,0.2421875, 16,0.2529296875, 17,0.263671875, 18,0.31103515625, 19,0.27685546875, 20,0.32666015625,0.16666666666666666 21,0.2490234375, 22,0.30810546875, 23,0.298828125, 24,0.29736328125, 25,0.322265625, 26,0.32080078125, 27,0.294921875, 28,0.3642578125, 29,0.35791015625, 30,0.37646484375,0.26666666666666666 31,0.4013671875, 32,0.3701171875, 33,0.38671875, 34,0.37158203125, 35,0.4462890625, 36,0.4091796875, 37,0.482421875, 38,0.38134765625, 39,0.40234375, 40,0.44482421875,0.26666666666666666 41,0.45556640625, 42,0.49609375, 43,0.4736328125, 44,0.44482421875, 45,0.4267578125, 46,0.4296875, 47,0.4482421875, 48,0.45458984375, 49,0.45263671875, 50,0.4833984375,0.23333333333333334 51,0.44873046875, 52,0.435546875, 53,0.4912109375, 54,0.39501953125, 55,0.4541015625, 56,0.498046875, 57,0.4716796875, 58,0.46337890625, 59,0.4521484375, 60,0.47998046875,0.26666666666666666 61,0.48095703125, 62,0.45556640625, 63,0.490234375, 64,0.4677734375, 65,0.4638671875, 66,0.4716796875, 67,0.4609375, 68,0.5009765625, 69,0.50146484375, 70,0.49560546875,0.26666666666666666 71,0.48779296875, 72,0.49755859375, 73,0.45166015625, 74,0.4609375, 75,0.5400390625, 76,0.48095703125, 77,0.5263671875, 78,0.5048828125, 79,0.4716796875, 80,0.4775390625,0.3 81,0.482421875, 82,0.49560546875, 83,0.49658203125, 84,0.486328125, 85,0.47509765625, 86,0.45458984375, 87,0.498046875, 88,0.52001953125, 89,0.4755859375, 90,0.47998046875,0.2 91,0.5126953125, 92,0.4990234375, 93,0.517578125, 94,0.4873046875, 95,0.51220703125, 96,0.482421875, 97,0.5205078125, 98,0.46875, 99,0.5322265625, 100,0.46826171875,0.26666666666666666