step,train_loss,train_accuracy,valid_loss,valid_mean_token_accuracy 1,15.81906,0.0,14.67002,0.0 2,13.07276,0.0,15.50881,0.0 3,13.87567,0.0,16.25,0.0 4,13.3373,0.0,12.77298,0.0 5,14.30848,0.0,12.6235,0.0 6,13.32132,0.0,11.60394,0.0 7,12.9074,0.0,11.67611,0.0 8,12.5918,0.0,9.70959,0.0 9,11.56537,0.0,8.65894,0.0 10,8.10063,0.0,15.49833,0.0 11,4.67463,0.0,4.4466,0.0 12,5.78812,0.0,3.59255,0.0 13,4.91947,0.0,1.81759,0.0 14,1.67461,0.0,1.37271,1.0 15,0.45382,1.0,0.02368,1.0 16,0.89798,1.0,0.05735,1.0 17,0.03383,1.0,0.03698,1.0 18,0.20682,1.0,0.00484,1.0 19,0.03163,1.0,0.00079,1.0 20,0.00083,1.0,0.00017,1.0 21,0.00013,1.0,4e-05,1.0 22,1e-05,1.0,1e-05,1.0 23,1e-05,1.0,0.0,1.0 24,0.0,1.0,0.0,1.0 25,0.0,1.0,2e-05,1.0 26,0.0,1.0,0.0,1.0 27,0.0,1.0,0.0,1.0 28,0.0,1.0,0.0,1.0 29,0.0,1.0,-0.0,1.0 30,0.0,1.0,0.99869,0.0 31,0.0,1.0,0.0,1.0 32,0.0,1.0,-0.0,1.0 33,0.0,1.0,-0.0,1.0 34,0.0,1.0,-0.0,1.0 35,0.0,1.0,-0.0,1.0 36,0.0,1.0,-0.0,1.0 37,0.0,1.0,-0.0,1.0 38,0.0,1.0,-0.0,1.0 39,0.0,1.0,-0.0,1.0 40,0.0,1.0,-0.0,1.0 41,0.0,1.0,-0.0,1.0 42,0.0,1.0,-0.0,1.0 43,0.0,1.0,-0.0,1.0 44,0.0,1.0,-0.0,1.0 45,0.0,1.0,0.0,1.0 46,0.0,1.0,-0.0,1.0 47,0.0,1.0,-0.0,1.0 48,1e-05,1.0,-0.0,1.0 49,0.0,1.0,0.0,1.0 50,0.0,1.0,9.84829,0.0 51,0.0,1.0,-0.0,1.0 52,0.0,1.0,-0.0,1.0 53,0.0,1.0,0.0,1.0 54,0.0,1.0,0.0,1.0 55,0.0,1.0,-0.0,1.0 56,0.0,1.0,0.0,1.0 57,0.0,1.0,-0.0,1.0 58,0.0,1.0,-0.0,1.0 59,0.0,1.0,-0.0,1.0 60,0.0,1.0,-0.0,1.0 61,0.0,1.0,0.0,1.0 62,0.0,1.0,-0.0,1.0 63,0.0,1.0,0.0,1.0 64,0.0,1.0,-0.0,1.0 65,0.0,1.0,-0.0,1.0 66,0.0,1.0,-0.0,1.0 67,0.0,1.0,-0.0,1.0 68,0.0,1.0,-0.0,1.0 69,0.0,1.0,0.0,1.0 70,0.0,1.0,9.45719,0.0 71,0.0,1.0,-0.0,1.0 72,0.0,1.0,-0.0,1.0 73,0.0,1.0,0.0,1.0 74,0.0,1.0,3e-05,1.0 75,0.0,1.0,0.0,1.0 76,0.0,1.0,0.0,1.0 77,0.0,1.0,0.0,1.0 78,0.0,1.0,0.0,1.0 79,0.0,1.0,-0.0,1.0 80,0.0,1.0,0.0,1.0