{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2461059190031152,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.012170583144449788,
      "learning_rate": 3e-05,
      "loss": 1.3728,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.012441205679409878,
      "learning_rate": 3e-05,
      "loss": 1.3427,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.012336052820426525,
      "learning_rate": 3e-05,
      "loss": 1.3983,
      "step": 3
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.013373499678550779,
      "learning_rate": 3e-05,
      "loss": 1.4146,
      "step": 4
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.016376857472937493,
      "learning_rate": 3e-05,
      "loss": 1.3665,
      "step": 5
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.01605485412905265,
      "learning_rate": 3e-05,
      "loss": 1.3865,
      "step": 6
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.01460238003538074,
      "learning_rate": 3e-05,
      "loss": 1.315,
      "step": 7
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.015553135144585159,
      "learning_rate": 3e-05,
      "loss": 1.3531,
      "step": 8
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.017868624998865858,
      "learning_rate": 3e-05,
      "loss": 1.3722,
      "step": 9
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.0164281315042581,
      "learning_rate": 3e-05,
      "loss": 1.3179,
      "step": 10
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.01913856813259346,
      "learning_rate": 3e-05,
      "loss": 1.3595,
      "step": 11
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0197227271190587,
      "learning_rate": 3e-05,
      "loss": 1.3904,
      "step": 12
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.02003628325196358,
      "learning_rate": 3e-05,
      "loss": 1.4069,
      "step": 13
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.020818781168561763,
      "learning_rate": 3e-05,
      "loss": 1.4516,
      "step": 14
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.020893517671768724,
      "learning_rate": 3e-05,
      "loss": 1.3407,
      "step": 15
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.02002708390520797,
      "learning_rate": 3e-05,
      "loss": 1.2756,
      "step": 16
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.02147346418874998,
      "learning_rate": 3e-05,
      "loss": 1.4446,
      "step": 17
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.026756951404830708,
      "learning_rate": 3e-05,
      "loss": 1.3975,
      "step": 18
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.02147348610321771,
      "learning_rate": 3e-05,
      "loss": 1.3954,
      "step": 19
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.02000891892461215,
      "learning_rate": 3e-05,
      "loss": 1.3254,
      "step": 20
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.02051820688028316,
      "learning_rate": 3e-05,
      "loss": 1.3688,
      "step": 21
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.019940598635671183,
      "learning_rate": 3e-05,
      "loss": 1.3304,
      "step": 22
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.019387442345986872,
      "learning_rate": 3e-05,
      "loss": 1.3422,
      "step": 23
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.024538417724117162,
      "learning_rate": 3e-05,
      "loss": 1.403,
      "step": 24
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.0197067247131013,
      "learning_rate": 3e-05,
      "loss": 1.3088,
      "step": 25
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.019906918553002587,
      "learning_rate": 3e-05,
      "loss": 1.3156,
      "step": 26
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.01690103579384712,
      "learning_rate": 3e-05,
      "loss": 1.3548,
      "step": 27
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.016146757145965005,
      "learning_rate": 3e-05,
      "loss": 1.323,
      "step": 28
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.015853850291687382,
      "learning_rate": 3e-05,
      "loss": 1.2991,
      "step": 29
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.014301767220445117,
      "learning_rate": 3e-05,
      "loss": 1.299,
      "step": 30
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.01456552708533801,
      "learning_rate": 3e-05,
      "loss": 1.327,
      "step": 31
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.014037544424116656,
      "learning_rate": 3e-05,
      "loss": 1.33,
      "step": 32
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.014164388239542412,
      "learning_rate": 3e-05,
      "loss": 1.3307,
      "step": 33
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.012972207094917622,
      "learning_rate": 3e-05,
      "loss": 1.3028,
      "step": 34
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.012981889713494583,
      "learning_rate": 3e-05,
      "loss": 1.2963,
      "step": 35
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.013445913227694615,
      "learning_rate": 3e-05,
      "loss": 1.2444,
      "step": 36
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.012792648708552297,
      "learning_rate": 3e-05,
      "loss": 1.26,
      "step": 37
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.012141794711979773,
      "learning_rate": 3e-05,
      "loss": 1.3438,
      "step": 38
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.013862600605300035,
      "learning_rate": 3e-05,
      "loss": 1.3285,
      "step": 39
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.012129096713587641,
      "learning_rate": 3e-05,
      "loss": 1.3221,
      "step": 40
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.01871167034290605,
      "learning_rate": 3e-05,
      "loss": 1.2861,
      "step": 41
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.012436045483287136,
      "learning_rate": 3e-05,
      "loss": 1.3068,
      "step": 42
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.012364790923012296,
      "learning_rate": 3e-05,
      "loss": 1.3156,
      "step": 43
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.012376437364947857,
      "learning_rate": 3e-05,
      "loss": 1.3088,
      "step": 44
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.013969833036331685,
      "learning_rate": 3e-05,
      "loss": 1.3316,
      "step": 45
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.012765341814671809,
      "learning_rate": 3e-05,
      "loss": 1.3352,
      "step": 46
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.01261010445191611,
      "learning_rate": 3e-05,
      "loss": 1.3144,
      "step": 47
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.012151618759459493,
      "learning_rate": 3e-05,
      "loss": 1.3204,
      "step": 48
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.012998675059932196,
      "learning_rate": 3e-05,
      "loss": 1.2887,
      "step": 49
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.012169489046924829,
      "learning_rate": 3e-05,
      "loss": 1.3332,
      "step": 50
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.011920646653506707,
      "learning_rate": 3e-05,
      "loss": 1.3553,
      "step": 51
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.011751923105885437,
      "learning_rate": 3e-05,
      "loss": 1.3671,
      "step": 52
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.011025753112968974,
      "learning_rate": 3e-05,
      "loss": 1.2771,
      "step": 53
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.012584882940640368,
      "learning_rate": 3e-05,
      "loss": 1.2277,
      "step": 54
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.01179619281685698,
      "learning_rate": 3e-05,
      "loss": 1.323,
      "step": 55
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.014564873082288777,
      "learning_rate": 3e-05,
      "loss": 1.2949,
      "step": 56
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.019435936977958635,
      "learning_rate": 3e-05,
      "loss": 1.3098,
      "step": 57
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.012111351048084126,
      "learning_rate": 3e-05,
      "loss": 1.3918,
      "step": 58
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.012162697288403175,
      "learning_rate": 3e-05,
      "loss": 1.2861,
      "step": 59
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.011286641826996159,
      "learning_rate": 3e-05,
      "loss": 1.316,
      "step": 60
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.014424400496857113,
      "learning_rate": 3e-05,
      "loss": 1.2717,
      "step": 61
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.011730736205609419,
      "learning_rate": 3e-05,
      "loss": 1.3252,
      "step": 62
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.011179658792604664,
      "learning_rate": 3e-05,
      "loss": 1.3211,
      "step": 63
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.011909295790935862,
      "learning_rate": 3e-05,
      "loss": 1.2757,
      "step": 64
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.013362118144354595,
      "learning_rate": 3e-05,
      "loss": 1.2457,
      "step": 65
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.019726440026194825,
      "learning_rate": 3e-05,
      "loss": 1.3159,
      "step": 66
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.01151143382587086,
      "learning_rate": 3e-05,
      "loss": 1.2628,
      "step": 67
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.011159675986273602,
      "learning_rate": 3e-05,
      "loss": 1.2901,
      "step": 68
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.01052362952035569,
      "learning_rate": 3e-05,
      "loss": 1.2749,
      "step": 69
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.014028722939171852,
      "learning_rate": 3e-05,
      "loss": 1.33,
      "step": 70
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.010897615932695505,
      "learning_rate": 3e-05,
      "loss": 1.3084,
      "step": 71
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.011353909572748124,
      "learning_rate": 3e-05,
      "loss": 1.277,
      "step": 72
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.011100433604844168,
      "learning_rate": 3e-05,
      "loss": 1.3586,
      "step": 73
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.011880796497294469,
      "learning_rate": 3e-05,
      "loss": 1.2959,
      "step": 74
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.011759412083305202,
      "learning_rate": 3e-05,
      "loss": 1.2957,
      "step": 75
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.011480127470140948,
      "learning_rate": 3e-05,
      "loss": 1.3278,
      "step": 76
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.011449384427383405,
      "learning_rate": 3e-05,
      "loss": 1.2633,
      "step": 77
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.011764058753943114,
      "learning_rate": 3e-05,
      "loss": 1.2808,
      "step": 78
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.01124430953679315,
      "learning_rate": 3e-05,
      "loss": 1.2664,
      "step": 79
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.01057061147022858,
      "learning_rate": 3e-05,
      "loss": 1.2969,
      "step": 80
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.011616218617106901,
      "learning_rate": 3e-05,
      "loss": 1.2982,
      "step": 81
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.01144732781571693,
      "learning_rate": 3e-05,
      "loss": 1.2784,
      "step": 82
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.011077640894084905,
      "learning_rate": 3e-05,
      "loss": 1.2819,
      "step": 83
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.01613205804007413,
      "learning_rate": 3e-05,
      "loss": 1.311,
      "step": 84
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.013574606375148299,
      "learning_rate": 3e-05,
      "loss": 1.2561,
      "step": 85
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.01335654343450743,
      "learning_rate": 3e-05,
      "loss": 1.2731,
      "step": 86
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.012449392909288468,
      "learning_rate": 3e-05,
      "loss": 1.2822,
      "step": 87
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.012435933132224748,
      "learning_rate": 3e-05,
      "loss": 1.2447,
      "step": 88
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.011302776757667351,
      "learning_rate": 3e-05,
      "loss": 1.2786,
      "step": 89
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.012040795209866716,
      "learning_rate": 3e-05,
      "loss": 1.3479,
      "step": 90
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.011073079422530921,
      "learning_rate": 3e-05,
      "loss": 1.2794,
      "step": 91
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.013030304746973722,
      "learning_rate": 3e-05,
      "loss": 1.3131,
      "step": 92
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.012526490354635381,
      "learning_rate": 3e-05,
      "loss": 1.2458,
      "step": 93
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.012847228081473072,
      "learning_rate": 3e-05,
      "loss": 1.2614,
      "step": 94
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.012688536258452844,
      "learning_rate": 3e-05,
      "loss": 1.2399,
      "step": 95
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.012208675458581508,
      "learning_rate": 3e-05,
      "loss": 1.3144,
      "step": 96
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.010859781351210412,
      "learning_rate": 3e-05,
      "loss": 1.2324,
      "step": 97
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.012478911974195483,
      "learning_rate": 3e-05,
      "loss": 1.2719,
      "step": 98
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.012373249769099943,
      "learning_rate": 3e-05,
      "loss": 1.2622,
      "step": 99
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.013463086982838338,
      "learning_rate": 3e-05,
      "loss": 1.2776,
      "step": 100
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.016385409822984896,
      "learning_rate": 3e-05,
      "loss": 1.2808,
      "step": 101
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.012219344462321249,
      "learning_rate": 3e-05,
      "loss": 1.3073,
      "step": 102
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.01219020267598617,
      "learning_rate": 3e-05,
      "loss": 1.2182,
      "step": 103
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.012387262921564371,
      "learning_rate": 3e-05,
      "loss": 1.3265,
      "step": 104
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.01206079560473451,
      "learning_rate": 3e-05,
      "loss": 1.2228,
      "step": 105
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.01225473000339032,
      "learning_rate": 3e-05,
      "loss": 1.2843,
      "step": 106
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.01326596734337093,
      "learning_rate": 3e-05,
      "loss": 1.2789,
      "step": 107
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.014527084891658,
      "learning_rate": 3e-05,
      "loss": 1.2407,
      "step": 108
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.013506152190492582,
      "learning_rate": 3e-05,
      "loss": 1.3537,
      "step": 109
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.012350713785703687,
      "learning_rate": 3e-05,
      "loss": 1.299,
      "step": 110
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.013548036090856945,
      "learning_rate": 3e-05,
      "loss": 1.3407,
      "step": 111
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.012716548388196138,
      "learning_rate": 3e-05,
      "loss": 1.2837,
      "step": 112
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.012376449836024567,
      "learning_rate": 3e-05,
      "loss": 1.2408,
      "step": 113
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.013149525793997427,
      "learning_rate": 3e-05,
      "loss": 1.2552,
      "step": 114
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.012168644210731216,
      "learning_rate": 3e-05,
      "loss": 1.3157,
      "step": 115
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.012324914288283324,
      "learning_rate": 3e-05,
      "loss": 1.3123,
      "step": 116
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.012072754893928983,
      "learning_rate": 3e-05,
      "loss": 1.2701,
      "step": 117
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.01264419972632402,
      "learning_rate": 3e-05,
      "loss": 1.2983,
      "step": 118
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.042949486922442916,
      "learning_rate": 3e-05,
      "loss": 1.3216,
      "step": 119
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.02568672309407492,
      "learning_rate": 3e-05,
      "loss": 1.3005,
      "step": 120
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.012811282089116556,
      "learning_rate": 3e-05,
      "loss": 1.3233,
      "step": 121
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.017868025898532574,
      "learning_rate": 3e-05,
      "loss": 1.3054,
      "step": 122
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.012993051949728001,
      "learning_rate": 3e-05,
      "loss": 1.2471,
      "step": 123
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.018403888249234238,
      "learning_rate": 3e-05,
      "loss": 1.3104,
      "step": 124
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.018015251441908964,
      "learning_rate": 3e-05,
      "loss": 1.2492,
      "step": 125
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.013906581394784246,
      "learning_rate": 3e-05,
      "loss": 1.2466,
      "step": 126
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.014862930320357416,
      "learning_rate": 3e-05,
      "loss": 1.3047,
      "step": 127
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.04412014629710122,
      "learning_rate": 3e-05,
      "loss": 1.2054,
      "step": 128
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.026614261465937473,
      "learning_rate": 3e-05,
      "loss": 1.2655,
      "step": 129
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.01376408626191131,
      "learning_rate": 3e-05,
      "loss": 1.2382,
      "step": 130
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.015429717937867932,
      "learning_rate": 3e-05,
      "loss": 1.3278,
      "step": 131
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.014533210702277371,
      "learning_rate": 3e-05,
      "loss": 1.3138,
      "step": 132
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.012982144097939177,
      "learning_rate": 3e-05,
      "loss": 1.3109,
      "step": 133
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.0182304886411741,
      "learning_rate": 3e-05,
      "loss": 1.2985,
      "step": 134
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.017093917039141884,
      "learning_rate": 3e-05,
      "loss": 1.2468,
      "step": 135
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.014512262916267834,
      "learning_rate": 3e-05,
      "loss": 1.3445,
      "step": 136
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.012373216012523584,
      "learning_rate": 3e-05,
      "loss": 1.2921,
      "step": 137
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.014913292517795098,
      "learning_rate": 3e-05,
      "loss": 1.3327,
      "step": 138
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.01548966880954737,
      "learning_rate": 3e-05,
      "loss": 1.3017,
      "step": 139
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.0140787411578127,
      "learning_rate": 3e-05,
      "loss": 1.3248,
      "step": 140
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.01421362111312793,
      "learning_rate": 3e-05,
      "loss": 1.3478,
      "step": 141
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.012945172730785133,
      "learning_rate": 3e-05,
      "loss": 1.2547,
      "step": 142
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.013197491856509017,
      "learning_rate": 3e-05,
      "loss": 1.2809,
      "step": 143
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.014138707993779835,
      "learning_rate": 3e-05,
      "loss": 1.2585,
      "step": 144
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.013999463137089363,
      "learning_rate": 3e-05,
      "loss": 1.316,
      "step": 145
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.014733166701341028,
      "learning_rate": 3e-05,
      "loss": 1.3576,
      "step": 146
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.012930967759936974,
      "learning_rate": 3e-05,
      "loss": 1.2939,
      "step": 147
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.013560296387293834,
      "learning_rate": 3e-05,
      "loss": 1.3307,
      "step": 148
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.017730136160404638,
      "learning_rate": 3e-05,
      "loss": 1.3118,
      "step": 149
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.013975982126514604,
      "learning_rate": 3e-05,
      "loss": 1.2836,
      "step": 150
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.013166737892207972,
      "learning_rate": 3e-05,
      "loss": 1.274,
      "step": 151
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.01341654728143307,
      "learning_rate": 3e-05,
      "loss": 1.2447,
      "step": 152
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.015608064826784552,
      "learning_rate": 3e-05,
      "loss": 1.2743,
      "step": 153
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.014402235915901979,
      "learning_rate": 3e-05,
      "loss": 1.2351,
      "step": 154
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.013660194729217125,
      "learning_rate": 3e-05,
      "loss": 1.2584,
      "step": 155
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.013437763813973025,
      "learning_rate": 3e-05,
      "loss": 1.2281,
      "step": 156
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.01391064432526438,
      "learning_rate": 3e-05,
      "loss": 1.2922,
      "step": 157
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.013854673514263218,
      "learning_rate": 3e-05,
      "loss": 1.2589,
      "step": 158
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.013357866419948893,
      "learning_rate": 3e-05,
      "loss": 1.3146,
      "step": 159
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.013746796253108871,
      "learning_rate": 3e-05,
      "loss": 1.2896,
      "step": 160
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.01323955577224082,
      "learning_rate": 3e-05,
      "loss": 1.2661,
      "step": 161
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.014094881922329888,
      "learning_rate": 3e-05,
      "loss": 1.2296,
      "step": 162
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.021786851768047143,
      "learning_rate": 3e-05,
      "loss": 1.3146,
      "step": 163
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.014115247163622169,
      "learning_rate": 3e-05,
      "loss": 1.2445,
      "step": 164
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.013235405572388292,
      "learning_rate": 3e-05,
      "loss": 1.2828,
      "step": 165
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.013292324416878417,
      "learning_rate": 3e-05,
      "loss": 1.2226,
      "step": 166
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.014395884061164101,
      "learning_rate": 3e-05,
      "loss": 1.3279,
      "step": 167
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.013904468976095652,
      "learning_rate": 3e-05,
      "loss": 1.3052,
      "step": 168
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.01498037832336143,
      "learning_rate": 3e-05,
      "loss": 1.2751,
      "step": 169
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.013935053913175984,
      "learning_rate": 3e-05,
      "loss": 1.2712,
      "step": 170
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.013342634505562194,
      "learning_rate": 3e-05,
      "loss": 1.2478,
      "step": 171
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.014280227334636308,
      "learning_rate": 3e-05,
      "loss": 1.2832,
      "step": 172
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.013662238228160744,
      "learning_rate": 3e-05,
      "loss": 1.3105,
      "step": 173
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.013883566745022063,
      "learning_rate": 3e-05,
      "loss": 1.2882,
      "step": 174
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.014231700687422954,
      "learning_rate": 3e-05,
      "loss": 1.3134,
      "step": 175
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.015856322519580097,
      "learning_rate": 3e-05,
      "loss": 1.3416,
      "step": 176
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.014864139947341821,
      "learning_rate": 3e-05,
      "loss": 1.2528,
      "step": 177
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.01384672514806748,
      "learning_rate": 3e-05,
      "loss": 1.2146,
      "step": 178
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.015464948934868796,
      "learning_rate": 3e-05,
      "loss": 1.2165,
      "step": 179
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.015385891583895897,
      "learning_rate": 3e-05,
      "loss": 1.3034,
      "step": 180
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.015500556463836994,
      "learning_rate": 3e-05,
      "loss": 1.2462,
      "step": 181
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.015360964744432567,
      "learning_rate": 3e-05,
      "loss": 1.2508,
      "step": 182
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.018104130847576297,
      "learning_rate": 3e-05,
      "loss": 1.2617,
      "step": 183
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.017297392951343114,
      "learning_rate": 3e-05,
      "loss": 1.2694,
      "step": 184
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.014605348589579433,
      "learning_rate": 3e-05,
      "loss": 1.2521,
      "step": 185
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.014287950283906567,
      "learning_rate": 3e-05,
      "loss": 1.2583,
      "step": 186
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.01496726177324148,
      "learning_rate": 3e-05,
      "loss": 1.2689,
      "step": 187
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.015097305854620989,
      "learning_rate": 3e-05,
      "loss": 1.3264,
      "step": 188
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.014393731181691946,
      "learning_rate": 3e-05,
      "loss": 1.2509,
      "step": 189
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.014329101467007178,
      "learning_rate": 3e-05,
      "loss": 1.2791,
      "step": 190
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.01432823143229832,
      "learning_rate": 3e-05,
      "loss": 1.3058,
      "step": 191
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.01409215280735208,
      "learning_rate": 3e-05,
      "loss": 1.298,
      "step": 192
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.014322129770126826,
      "learning_rate": 3e-05,
      "loss": 1.2822,
      "step": 193
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.015535730832931206,
      "learning_rate": 3e-05,
      "loss": 1.2952,
      "step": 194
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.014586001705999283,
      "learning_rate": 3e-05,
      "loss": 1.2916,
      "step": 195
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.014346450671961445,
      "learning_rate": 3e-05,
      "loss": 1.286,
      "step": 196
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.01465216301040808,
      "learning_rate": 3e-05,
      "loss": 1.3168,
      "step": 197
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.014633342656678221,
      "learning_rate": 3e-05,
      "loss": 1.222,
      "step": 198
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.019433028609002513,
      "learning_rate": 3e-05,
      "loss": 1.2868,
      "step": 199
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.015999291729556466,
      "learning_rate": 3e-05,
      "loss": 1.2546,
      "step": 200
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.013974319782604303,
      "learning_rate": 3e-05,
      "loss": 1.3313,
      "step": 201
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.019684778346554094,
      "learning_rate": 3e-05,
      "loss": 1.2183,
      "step": 202
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.033028122367380335,
      "learning_rate": 3e-05,
      "loss": 1.2943,
      "step": 203
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.015226007463866797,
      "learning_rate": 3e-05,
      "loss": 1.2398,
      "step": 204
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.018039902586464752,
      "learning_rate": 3e-05,
      "loss": 1.2804,
      "step": 205
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.01458863130389662,
      "learning_rate": 3e-05,
      "loss": 1.3344,
      "step": 206
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.015824538304288215,
      "learning_rate": 3e-05,
      "loss": 1.2351,
      "step": 207
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.014833851868165835,
      "learning_rate": 3e-05,
      "loss": 1.2385,
      "step": 208
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.013926386093476583,
      "learning_rate": 3e-05,
      "loss": 1.2263,
      "step": 209
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.015632500062928826,
      "learning_rate": 3e-05,
      "loss": 1.2931,
      "step": 210
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.014724285681248521,
      "learning_rate": 3e-05,
      "loss": 1.3084,
      "step": 211
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.014461044938261114,
      "learning_rate": 3e-05,
      "loss": 1.3348,
      "step": 212
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.014888010433011196,
      "learning_rate": 3e-05,
      "loss": 1.2726,
      "step": 213
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.015186640580123631,
      "learning_rate": 3e-05,
      "loss": 1.266,
      "step": 214
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.014169851274828012,
      "learning_rate": 3e-05,
      "loss": 1.2275,
      "step": 215
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.014597768020650003,
      "learning_rate": 3e-05,
      "loss": 1.166,
      "step": 216
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.016348049435478462,
      "learning_rate": 3e-05,
      "loss": 1.3315,
      "step": 217
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.01389791869445101,
      "learning_rate": 3e-05,
      "loss": 1.2339,
      "step": 218
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.014730542143538614,
      "learning_rate": 3e-05,
      "loss": 1.2884,
      "step": 219
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.01495965630015944,
      "learning_rate": 3e-05,
      "loss": 1.1792,
      "step": 220
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.016164599847288814,
      "learning_rate": 3e-05,
      "loss": 1.2511,
      "step": 221
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.014356323440192154,
      "learning_rate": 3e-05,
      "loss": 1.2653,
      "step": 222
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.014496008840759921,
      "learning_rate": 3e-05,
      "loss": 1.3067,
      "step": 223
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.014173980530200598,
      "learning_rate": 3e-05,
      "loss": 1.1765,
      "step": 224
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.019941463494425323,
      "learning_rate": 3e-05,
      "loss": 1.2627,
      "step": 225
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.014559827444157727,
      "learning_rate": 3e-05,
      "loss": 1.2726,
      "step": 226
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.015633910509735647,
      "learning_rate": 3e-05,
      "loss": 1.2062,
      "step": 227
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.014734762194709058,
      "learning_rate": 3e-05,
      "loss": 1.2472,
      "step": 228
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.014923021609054498,
      "learning_rate": 3e-05,
      "loss": 1.2648,
      "step": 229
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.01609643463392318,
      "learning_rate": 3e-05,
      "loss": 1.3097,
      "step": 230
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.015313840216276563,
      "learning_rate": 3e-05,
      "loss": 1.2462,
      "step": 231
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.014704752471017907,
      "learning_rate": 3e-05,
      "loss": 1.2852,
      "step": 232
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.01565975211378067,
      "learning_rate": 3e-05,
      "loss": 1.2879,
      "step": 233
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.014461185719430197,
      "learning_rate": 3e-05,
      "loss": 1.2475,
      "step": 234
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.015730123295533558,
      "learning_rate": 3e-05,
      "loss": 1.3275,
      "step": 235
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.014412110316894376,
      "learning_rate": 3e-05,
      "loss": 1.2307,
      "step": 236
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.014929677218383007,
      "learning_rate": 3e-05,
      "loss": 1.2575,
      "step": 237
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.015039383819204387,
      "learning_rate": 3e-05,
      "loss": 1.2906,
      "step": 238
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.01682053180538288,
      "learning_rate": 3e-05,
      "loss": 1.2758,
      "step": 239
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.014600617493742423,
      "learning_rate": 3e-05,
      "loss": 1.2972,
      "step": 240
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.01713356030477511,
      "learning_rate": 3e-05,
      "loss": 1.23,
      "step": 241
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.013713370678298656,
      "learning_rate": 3e-05,
      "loss": 1.2082,
      "step": 242
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.016029060499359975,
      "learning_rate": 3e-05,
      "loss": 1.2185,
      "step": 243
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.01455024577177708,
      "learning_rate": 3e-05,
      "loss": 1.3149,
      "step": 244
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.01596055912900773,
      "learning_rate": 3e-05,
      "loss": 1.2845,
      "step": 245
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.015210011602171563,
      "learning_rate": 3e-05,
      "loss": 1.2585,
      "step": 246
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.015453757198715246,
      "learning_rate": 3e-05,
      "loss": 1.2693,
      "step": 247
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.01610457228670694,
      "learning_rate": 3e-05,
      "loss": 1.2811,
      "step": 248
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.015836760290716817,
      "learning_rate": 3e-05,
      "loss": 1.3358,
      "step": 249
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.015349071831974473,
      "learning_rate": 3e-05,
      "loss": 1.2107,
      "step": 250
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.016164039133739174,
      "learning_rate": 3e-05,
      "loss": 1.2893,
      "step": 251
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.0159590525586263,
      "learning_rate": 3e-05,
      "loss": 1.2611,
      "step": 252
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.01565613651294786,
      "learning_rate": 3e-05,
      "loss": 1.2711,
      "step": 253
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.014721531061888017,
      "learning_rate": 3e-05,
      "loss": 1.2482,
      "step": 254
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.01753826817531843,
      "learning_rate": 3e-05,
      "loss": 1.2687,
      "step": 255
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.015353098066933114,
      "learning_rate": 3e-05,
      "loss": 1.2904,
      "step": 256
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.015204215112422145,
      "learning_rate": 3e-05,
      "loss": 1.2441,
      "step": 257
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.01627876478176434,
      "learning_rate": 3e-05,
      "loss": 1.2617,
      "step": 258
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.015173324308372222,
      "learning_rate": 3e-05,
      "loss": 1.2161,
      "step": 259
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.01821412576469944,
      "learning_rate": 3e-05,
      "loss": 1.2901,
      "step": 260
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.06506686696796124,
      "learning_rate": 3e-05,
      "loss": 1.2874,
      "step": 261
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.01729616604201323,
      "learning_rate": 3e-05,
      "loss": 1.2356,
      "step": 262
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.01675033762473565,
      "learning_rate": 3e-05,
      "loss": 1.236,
      "step": 263
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.02192888065943148,
      "learning_rate": 3e-05,
      "loss": 1.2421,
      "step": 264
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.016455712121954427,
      "learning_rate": 3e-05,
      "loss": 1.247,
      "step": 265
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.01814348646038703,
      "learning_rate": 3e-05,
      "loss": 1.2485,
      "step": 266
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.01567451038250417,
      "learning_rate": 3e-05,
      "loss": 1.3521,
      "step": 267
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.016734589709319087,
      "learning_rate": 3e-05,
      "loss": 1.3147,
      "step": 268
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.01665607669544241,
      "learning_rate": 3e-05,
      "loss": 1.2557,
      "step": 269
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.015340602915616324,
      "learning_rate": 3e-05,
      "loss": 1.217,
      "step": 270
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.015484796323673096,
      "learning_rate": 3e-05,
      "loss": 1.2644,
      "step": 271
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.01882586923200815,
      "learning_rate": 3e-05,
      "loss": 1.3565,
      "step": 272
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.01809392578664252,
      "learning_rate": 3e-05,
      "loss": 1.2218,
      "step": 273
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.01611243987811714,
      "learning_rate": 3e-05,
      "loss": 1.3112,
      "step": 274
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.015800275555133508,
      "learning_rate": 3e-05,
      "loss": 1.253,
      "step": 275
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.024573084585391664,
      "learning_rate": 3e-05,
      "loss": 1.3009,
      "step": 276
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.074452403888149,
      "learning_rate": 3e-05,
      "loss": 1.2592,
      "step": 277
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.017056904078373382,
      "learning_rate": 3e-05,
      "loss": 1.2774,
      "step": 278
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.01821583975502332,
      "learning_rate": 3e-05,
      "loss": 1.1952,
      "step": 279
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.015751526406141428,
      "learning_rate": 3e-05,
      "loss": 1.2365,
      "step": 280
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.015753098191682944,
      "learning_rate": 3e-05,
      "loss": 1.2847,
      "step": 281
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.01588334509784229,
      "learning_rate": 3e-05,
      "loss": 1.3455,
      "step": 282
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.016152905035665025,
      "learning_rate": 3e-05,
      "loss": 1.2748,
      "step": 283
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.015193625382186535,
      "learning_rate": 3e-05,
      "loss": 1.2911,
      "step": 284
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.015901242732867416,
      "learning_rate": 3e-05,
      "loss": 1.2784,
      "step": 285
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.016971976726614598,
      "learning_rate": 3e-05,
      "loss": 1.2659,
      "step": 286
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.01612818830639207,
      "learning_rate": 3e-05,
      "loss": 1.2668,
      "step": 287
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.017395387712717487,
      "learning_rate": 3e-05,
      "loss": 1.3022,
      "step": 288
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.01731193234013385,
      "learning_rate": 3e-05,
      "loss": 1.2033,
      "step": 289
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.01651302780868134,
      "learning_rate": 3e-05,
      "loss": 1.251,
      "step": 290
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.01646013792423402,
      "learning_rate": 3e-05,
      "loss": 1.3053,
      "step": 291
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.016605424458919063,
      "learning_rate": 3e-05,
      "loss": 1.2226,
      "step": 292
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.01642401242189507,
      "learning_rate": 3e-05,
      "loss": 1.2478,
      "step": 293
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.020526048019968234,
      "learning_rate": 3e-05,
      "loss": 1.2803,
      "step": 294
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.015357937815369777,
      "learning_rate": 3e-05,
      "loss": 1.3025,
      "step": 295
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.01661270914190639,
      "learning_rate": 3e-05,
      "loss": 1.297,
      "step": 296
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.017421945864776314,
      "learning_rate": 3e-05,
      "loss": 1.2958,
      "step": 297
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.017204965850903572,
      "learning_rate": 3e-05,
      "loss": 1.2675,
      "step": 298
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.016739239213025746,
      "learning_rate": 3e-05,
      "loss": 1.2631,
      "step": 299
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.015307923198409266,
      "learning_rate": 3e-05,
      "loss": 1.2664,
      "step": 300
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 480,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "total_flos": 4174125975207936.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}