{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.154929577464788,
  "eval_steps": 100,
  "global_step": 340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 5e-06,
      "loss": 1.5896,
      "step": 1
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.6521,
      "step": 2
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.5e-05,
      "loss": 1.3654,
      "step": 3
    },
    {
      "epoch": 0.23,
      "learning_rate": 2e-05,
      "loss": 1.3569,
      "step": 4
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.5e-05,
      "loss": 1.4352,
      "step": 5
    },
    {
      "epoch": 0.34,
      "learning_rate": 3e-05,
      "loss": 1.425,
      "step": 6
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.5e-05,
      "loss": 1.3529,
      "step": 7
    },
    {
      "epoch": 0.45,
      "learning_rate": 4e-05,
      "loss": 1.384,
      "step": 8
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.5e-05,
      "loss": 1.3881,
      "step": 9
    },
    {
      "epoch": 0.56,
      "learning_rate": 5e-05,
      "loss": 1.5593,
      "step": 10
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.999886713385432e-05,
      "loss": 1.3423,
      "step": 11
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.999546863808815e-05,
      "loss": 1.4725,
      "step": 12
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.9989804820704735e-05,
      "loss": 1.4342,
      "step": 13
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.9981876195011844e-05,
      "loss": 1.3769,
      "step": 14
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.99716834795752e-05,
      "loss": 1.3976,
      "step": 15
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.995922759815339e-05,
      "loss": 1.328,
      "step": 16
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.994450967961413e-05,
      "loss": 1.266,
      "step": 17
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.992753105783194e-05,
      "loss": 1.4671,
      "step": 18
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.9908293271567286e-05,
      "loss": 1.3973,
      "step": 19
    },
    {
      "epoch": 1.13,
      "learning_rate": 4.988679806432712e-05,
      "loss": 1.3835,
      "step": 20
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.9863047384206835e-05,
      "loss": 1.2203,
      "step": 21
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.9837043383713753e-05,
      "loss": 1.3752,
      "step": 22
    },
    {
      "epoch": 1.3,
      "learning_rate": 4.980878841957203e-05,
      "loss": 1.4142,
      "step": 23
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.977828505250903e-05,
      "loss": 1.3657,
      "step": 24
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.9745536047023324e-05,
      "loss": 1.309,
      "step": 25
    },
    {
      "epoch": 1.46,
      "learning_rate": 4.971054437113406e-05,
      "loss": 1.3004,
      "step": 26
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.967331319611206e-05,
      "loss": 1.3309,
      "step": 27
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.963384589619233e-05,
      "loss": 1.4956,
      "step": 28
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.959214604826831e-05,
      "loss": 1.2682,
      "step": 29
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.9548217431567665e-05,
      "loss": 1.391,
      "step": 30
    },
    {
      "epoch": 1.75,
      "learning_rate": 4.9502064027309836e-05,
      "loss": 1.3102,
      "step": 31
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.9453690018345144e-05,
      "loss": 1.3891,
      "step": 32
    },
    {
      "epoch": 1.86,
      "learning_rate": 4.9403099788775754e-05,
      "loss": 1.3538,
      "step": 33
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.935029792355834e-05,
      "loss": 1.3443,
      "step": 34
    },
    {
      "epoch": 1.97,
      "learning_rate": 4.929528920808854e-05,
      "loss": 1.3384,
      "step": 35
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.923807862776728e-05,
      "loss": 1.2968,
      "step": 36
    },
    {
      "epoch": 2.08,
      "learning_rate": 4.917867136754893e-05,
      "loss": 1.2624,
      "step": 37
    },
    {
      "epoch": 2.14,
      "learning_rate": 4.91170728114714e-05,
      "loss": 1.3547,
      "step": 38
    },
    {
      "epoch": 2.2,
      "learning_rate": 4.9053288542168185e-05,
      "loss": 1.3857,
      "step": 39
    },
    {
      "epoch": 2.25,
      "learning_rate": 4.898732434036244e-05,
      "loss": 1.2261,
      "step": 40
    },
    {
      "epoch": 2.31,
      "learning_rate": 4.8919186184343046e-05,
      "loss": 1.4072,
      "step": 41
    },
    {
      "epoch": 2.37,
      "learning_rate": 4.8848880249422815e-05,
      "loss": 1.3283,
      "step": 42
    },
    {
      "epoch": 2.42,
      "learning_rate": 4.877641290737884e-05,
      "loss": 1.2464,
      "step": 43
    },
    {
      "epoch": 2.48,
      "learning_rate": 4.870179072587499e-05,
      "loss": 1.3433,
      "step": 44
    },
    {
      "epoch": 2.54,
      "learning_rate": 4.862502046786671e-05,
      "loss": 1.2861,
      "step": 45
    },
    {
      "epoch": 2.59,
      "learning_rate": 4.854610909098812e-05,
      "loss": 1.1888,
      "step": 46
    },
    {
      "epoch": 2.65,
      "learning_rate": 4.8465063746921395e-05,
      "loss": 1.2509,
      "step": 47
    },
    {
      "epoch": 2.7,
      "learning_rate": 4.838189178074867e-05,
      "loss": 1.4449,
      "step": 48
    },
    {
      "epoch": 2.76,
      "learning_rate": 4.829660073028631e-05,
      "loss": 1.4645,
      "step": 49
    },
    {
      "epoch": 2.82,
      "learning_rate": 4.8209198325401815e-05,
      "loss": 1.3586,
      "step": 50
    },
    {
      "epoch": 2.87,
      "learning_rate": 4.811969248731323e-05,
      "loss": 1.3542,
      "step": 51
    },
    {
      "epoch": 2.93,
      "learning_rate": 4.802809132787125e-05,
      "loss": 1.3145,
      "step": 52
    },
    {
      "epoch": 2.99,
      "learning_rate": 4.793440314882408e-05,
      "loss": 1.2343,
      "step": 53
    },
    {
      "epoch": 3.04,
      "learning_rate": 4.783863644106502e-05,
      "loss": 1.2946,
      "step": 54
    },
    {
      "epoch": 3.1,
      "learning_rate": 4.774079988386296e-05,
      "loss": 1.2621,
      "step": 55
    },
    {
      "epoch": 3.15,
      "learning_rate": 4.764090234407577e-05,
      "loss": 1.3581,
      "step": 56
    },
    {
      "epoch": 3.21,
      "learning_rate": 4.753895287534673e-05,
      "loss": 1.3891,
      "step": 57
    },
    {
      "epoch": 3.27,
      "learning_rate": 4.743496071728396e-05,
      "loss": 1.334,
      "step": 58
    },
    {
      "epoch": 3.32,
      "learning_rate": 4.73289352946231e-05,
      "loss": 1.3105,
      "step": 59
    },
    {
      "epoch": 3.38,
      "learning_rate": 4.722088621637309e-05,
      "loss": 1.2921,
      "step": 60
    },
    {
      "epoch": 3.44,
      "learning_rate": 4.711082327494536e-05,
      "loss": 1.2406,
      "step": 61
    },
    {
      "epoch": 3.49,
      "learning_rate": 4.6998756445266336e-05,
      "loss": 1.4246,
      "step": 62
    },
    {
      "epoch": 3.55,
      "learning_rate": 4.688469588387339e-05,
      "loss": 1.2126,
      "step": 63
    },
    {
      "epoch": 3.61,
      "learning_rate": 4.6768651927994434e-05,
      "loss": 1.3662,
      "step": 64
    },
    {
      "epoch": 3.66,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.2044,
      "step": 65
    },
    {
      "epoch": 3.72,
      "learning_rate": 4.653065607950502e-05,
      "loss": 1.4344,
      "step": 66
    },
    {
      "epoch": 3.77,
      "learning_rate": 4.640872575628973e-05,
      "loss": 1.3652,
      "step": 67
    },
    {
      "epoch": 3.83,
      "learning_rate": 4.628485517542392e-05,
      "loss": 1.231,
      "step": 68
    },
    {
      "epoch": 3.89,
      "learning_rate": 4.6159055563210604e-05,
      "loss": 1.1948,
      "step": 69
    },
    {
      "epoch": 3.94,
      "learning_rate": 4.6031338320779534e-05,
      "loss": 1.2484,
      "step": 70
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.59017150230539e-05,
      "loss": 1.2968,
      "step": 71
    },
    {
      "epoch": 4.06,
      "learning_rate": 4.5770197417701365e-05,
      "loss": 1.1691,
      "step": 72
    },
    {
      "epoch": 4.11,
      "learning_rate": 4.563679742406935e-05,
      "loss": 1.224,
      "step": 73
    },
    {
      "epoch": 4.17,
      "learning_rate": 4.550152713210478e-05,
      "loss": 1.2669,
      "step": 74
    },
    {
      "epoch": 4.23,
      "learning_rate": 4.5364398801258396e-05,
      "loss": 1.3218,
      "step": 75
    },
    {
      "epoch": 4.28,
      "learning_rate": 4.522542485937369e-05,
      "loss": 1.3309,
      "step": 76
    },
    {
      "epoch": 4.34,
      "learning_rate": 4.508461790156056e-05,
      "loss": 1.3356,
      "step": 77
    },
    {
      "epoch": 4.39,
      "learning_rate": 4.4941990689053886e-05,
      "loss": 1.3367,
      "step": 78
    },
    {
      "epoch": 4.45,
      "learning_rate": 4.479755614805688e-05,
      "loss": 1.3568,
      "step": 79
    },
    {
      "epoch": 4.51,
      "learning_rate": 4.465132736856969e-05,
      "loss": 1.29,
      "step": 80
    },
    {
      "epoch": 4.56,
      "learning_rate": 4.450331760320302e-05,
      "loss": 1.3522,
      "step": 81
    },
    {
      "epoch": 4.62,
      "learning_rate": 4.4353540265977064e-05,
      "loss": 1.3021,
      "step": 82
    },
    {
      "epoch": 4.68,
      "learning_rate": 4.4202008931105795e-05,
      "loss": 1.303,
      "step": 83
    },
    {
      "epoch": 4.73,
      "learning_rate": 4.404873733176678e-05,
      "loss": 1.313,
      "step": 84
    },
    {
      "epoch": 4.79,
      "learning_rate": 4.389373935885646e-05,
      "loss": 1.231,
      "step": 85
    },
    {
      "epoch": 4.85,
      "learning_rate": 4.373702905973135e-05,
      "loss": 1.2908,
      "step": 86
    },
    {
      "epoch": 4.9,
      "learning_rate": 4.357862063693486e-05,
      "loss": 1.2575,
      "step": 87
    },
    {
      "epoch": 4.96,
      "learning_rate": 4.341852844691012e-05,
      "loss": 1.1942,
      "step": 88
    },
    {
      "epoch": 5.01,
      "learning_rate": 4.3256766998698936e-05,
      "loss": 1.1607,
      "step": 89
    },
    {
      "epoch": 5.07,
      "learning_rate": 4.309335095262676e-05,
      "loss": 1.3386,
      "step": 90
    },
    {
      "epoch": 5.13,
      "learning_rate": 4.292829511897409e-05,
      "loss": 1.371,
      "step": 91
    },
    {
      "epoch": 5.18,
      "learning_rate": 4.276161445663423e-05,
      "loss": 1.236,
      "step": 92
    },
    {
      "epoch": 5.24,
      "learning_rate": 4.259332407175751e-05,
      "loss": 1.2531,
      "step": 93
    },
    {
      "epoch": 5.3,
      "learning_rate": 4.242343921638234e-05,
      "loss": 1.2593,
      "step": 94
    },
    {
      "epoch": 5.35,
      "learning_rate": 4.2251975287052804e-05,
      "loss": 1.1245,
      "step": 95
    },
    {
      "epoch": 5.41,
      "learning_rate": 4.2078947823423364e-05,
      "loss": 1.2538,
      "step": 96
    },
    {
      "epoch": 5.46,
      "learning_rate": 4.1904372506850484e-05,
      "loss": 1.2847,
      "step": 97
    },
    {
      "epoch": 5.52,
      "learning_rate": 4.172826515897146e-05,
      "loss": 1.2071,
      "step": 98
    },
    {
      "epoch": 5.58,
      "learning_rate": 4.155064174027047e-05,
      "loss": 1.2664,
      "step": 99
    },
    {
      "epoch": 5.63,
      "learning_rate": 4.137151834863213e-05,
      "loss": 1.1919,
      "step": 100
    },
    {
      "epoch": 5.63,
      "eval_loss": 1.2261024713516235,
      "eval_runtime": 1.4353,
      "eval_samples_per_second": 6.967,
      "eval_steps_per_second": 3.484,
      "step": 100
    },
    {
      "epoch": 5.69,
      "learning_rate": 4.119091121788256e-05,
      "loss": 1.1509,
      "step": 101
    },
    {
      "epoch": 5.75,
      "learning_rate": 4.100883671631806e-05,
      "loss": 1.3013,
      "step": 102
    },
    {
      "epoch": 5.8,
      "learning_rate": 4.082531134522176e-05,
      "loss": 1.313,
      "step": 103
    },
    {
      "epoch": 5.86,
      "learning_rate": 4.064035173736804e-05,
      "loss": 1.2176,
      "step": 104
    },
    {
      "epoch": 5.92,
      "learning_rate": 4.045397465551513e-05,
      "loss": 1.1004,
      "step": 105
    },
    {
      "epoch": 5.97,
      "learning_rate": 4.0266196990885955e-05,
      "loss": 1.3575,
      "step": 106
    },
    {
      "epoch": 6.03,
      "learning_rate": 4.007703576163724e-05,
      "loss": 1.2923,
      "step": 107
    },
    {
      "epoch": 6.08,
      "learning_rate": 3.98865081113172e-05,
      "loss": 1.2083,
      "step": 108
    },
    {
      "epoch": 6.14,
      "learning_rate": 3.969463130731183e-05,
      "loss": 1.2141,
      "step": 109
    },
    {
      "epoch": 6.2,
      "learning_rate": 3.9501422739279956e-05,
      "loss": 1.3297,
      "step": 110
    },
    {
      "epoch": 6.25,
      "learning_rate": 3.9306899917577245e-05,
      "loss": 1.0901,
      "step": 111
    },
    {
      "epoch": 6.31,
      "learning_rate": 3.911108047166924e-05,
      "loss": 1.2235,
      "step": 112
    },
    {
      "epoch": 6.37,
      "learning_rate": 3.89139821485336e-05,
      "loss": 1.341,
      "step": 113
    },
    {
      "epoch": 6.42,
      "learning_rate": 3.871562281105175e-05,
      "loss": 1.362,
      "step": 114
    },
    {
      "epoch": 6.48,
      "learning_rate": 3.851602043638994e-05,
      "loss": 1.2738,
      "step": 115
    },
    {
      "epoch": 6.54,
      "learning_rate": 3.8315193114369996e-05,
      "loss": 1.2264,
      "step": 116
    },
    {
      "epoch": 6.59,
      "learning_rate": 3.8113159045829864e-05,
      "loss": 1.171,
      "step": 117
    },
    {
      "epoch": 6.65,
      "learning_rate": 3.790993654097405e-05,
      "loss": 1.1848,
      "step": 118
    },
    {
      "epoch": 6.7,
      "learning_rate": 3.770554401771423e-05,
      "loss": 1.1545,
      "step": 119
    },
    {
      "epoch": 6.76,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.2799,
      "step": 120
    },
    {
      "epoch": 6.82,
      "learning_rate": 3.72933231161401e-05,
      "loss": 1.2278,
      "step": 121
    },
    {
      "epoch": 6.87,
      "learning_rate": 3.708553209711409e-05,
      "loss": 1.1959,
      "step": 122
    },
    {
      "epoch": 6.93,
      "learning_rate": 3.6876645774874876e-05,
      "loss": 1.1151,
      "step": 123
    },
    {
      "epoch": 6.99,
      "learning_rate": 3.6666683080641846e-05,
      "loss": 1.2178,
      "step": 124
    },
    {
      "epoch": 7.04,
      "learning_rate": 3.645566304318526e-05,
      "loss": 1.1584,
      "step": 125
    },
    {
      "epoch": 7.1,
      "learning_rate": 3.624360478710165e-05,
      "loss": 1.0959,
      "step": 126
    },
    {
      "epoch": 7.15,
      "learning_rate": 3.603052753108053e-05,
      "loss": 1.3026,
      "step": 127
    },
    {
      "epoch": 7.21,
      "learning_rate": 3.581645058616271e-05,
      "loss": 1.2007,
      "step": 128
    },
    {
      "epoch": 7.27,
      "learning_rate": 3.5601393353990046e-05,
      "loss": 1.2242,
      "step": 129
    },
    {
      "epoch": 7.32,
      "learning_rate": 3.5385375325047166e-05,
      "loss": 1.2737,
      "step": 130
    },
    {
      "epoch": 7.38,
      "learning_rate": 3.516841607689501e-05,
      "loss": 1.2724,
      "step": 131
    },
    {
      "epoch": 7.44,
      "learning_rate": 3.495053527239656e-05,
      "loss": 1.1916,
      "step": 132
    },
    {
      "epoch": 7.49,
      "learning_rate": 3.4731752657934794e-05,
      "loss": 1.2107,
      "step": 133
    },
    {
      "epoch": 7.55,
      "learning_rate": 3.4512088061623075e-05,
      "loss": 1.246,
      "step": 134
    },
    {
      "epoch": 7.61,
      "learning_rate": 3.4291561391508185e-05,
      "loss": 1.1841,
      "step": 135
    },
    {
      "epoch": 7.66,
      "learning_rate": 3.4070192633766025e-05,
      "loss": 1.1898,
      "step": 136
    },
    {
      "epoch": 7.72,
      "learning_rate": 3.3848001850890296e-05,
      "loss": 1.1195,
      "step": 137
    },
    {
      "epoch": 7.77,
      "learning_rate": 3.3625009179874265e-05,
      "loss": 1.1685,
      "step": 138
    },
    {
      "epoch": 7.83,
      "learning_rate": 3.3401234830385756e-05,
      "loss": 1.2748,
      "step": 139
    },
    {
      "epoch": 7.89,
      "learning_rate": 3.3176699082935545e-05,
      "loss": 1.1697,
      "step": 140
    },
    {
      "epoch": 7.94,
      "learning_rate": 3.295142228703938e-05,
      "loss": 1.1624,
      "step": 141
    },
    {
      "epoch": 8.0,
      "learning_rate": 3.272542485937369e-05,
      "loss": 1.1679,
      "step": 142
    },
    {
      "epoch": 8.06,
      "learning_rate": 3.249872728192527e-05,
      "loss": 1.1163,
      "step": 143
    },
    {
      "epoch": 8.11,
      "learning_rate": 3.2271350100134975e-05,
      "loss": 1.1319,
      "step": 144
    },
    {
      "epoch": 8.17,
      "learning_rate": 3.2043313921035743e-05,
      "loss": 1.2151,
      "step": 145
    },
    {
      "epoch": 8.23,
      "learning_rate": 3.181463941138495e-05,
      "loss": 1.1339,
      "step": 146
    },
    {
      "epoch": 8.28,
      "learning_rate": 3.158534729579142e-05,
      "loss": 1.1503,
      "step": 147
    },
    {
      "epoch": 8.34,
      "learning_rate": 3.135545835483718e-05,
      "loss": 1.2326,
      "step": 148
    },
    {
      "epoch": 8.39,
      "learning_rate": 3.11249934231941e-05,
      "loss": 1.2938,
      "step": 149
    },
    {
      "epoch": 8.45,
      "learning_rate": 3.0893973387735687e-05,
      "loss": 1.1454,
      "step": 150
    },
    {
      "epoch": 8.51,
      "learning_rate": 3.0662419185644115e-05,
      "loss": 1.2504,
      "step": 151
    },
    {
      "epoch": 8.56,
      "learning_rate": 3.0430351802512698e-05,
      "loss": 0.987,
      "step": 152
    },
    {
      "epoch": 8.62,
      "learning_rate": 3.0197792270443982e-05,
      "loss": 1.1387,
      "step": 153
    },
    {
      "epoch": 8.68,
      "learning_rate": 2.996476166614364e-05,
      "loss": 1.1142,
      "step": 154
    },
    {
      "epoch": 8.73,
      "learning_rate": 2.9731281109010256e-05,
      "loss": 1.1714,
      "step": 155
    },
    {
      "epoch": 8.79,
      "learning_rate": 2.9497371759221347e-05,
      "loss": 1.1858,
      "step": 156
    },
    {
      "epoch": 8.85,
      "learning_rate": 2.92630548158156e-05,
      "loss": 1.2169,
      "step": 157
    },
    {
      "epoch": 8.9,
      "learning_rate": 2.9028351514771606e-05,
      "loss": 1.2204,
      "step": 158
    },
    {
      "epoch": 8.96,
      "learning_rate": 2.8793283127083292e-05,
      "loss": 1.0313,
      "step": 159
    },
    {
      "epoch": 9.01,
      "learning_rate": 2.8557870956832132e-05,
      "loss": 1.2432,
      "step": 160
    },
    {
      "epoch": 9.07,
      "learning_rate": 2.8322136339256356e-05,
      "loss": 1.0614,
      "step": 161
    },
    {
      "epoch": 9.13,
      "learning_rate": 2.808610063881737e-05,
      "loss": 1.1682,
      "step": 162
    },
    {
      "epoch": 9.18,
      "learning_rate": 2.7849785247263515e-05,
      "loss": 1.0238,
      "step": 163
    },
    {
      "epoch": 9.24,
      "learning_rate": 2.761321158169134e-05,
      "loss": 1.166,
      "step": 164
    },
    {
      "epoch": 9.3,
      "learning_rate": 2.7376401082604564e-05,
      "loss": 1.0965,
      "step": 165
    },
    {
      "epoch": 9.35,
      "learning_rate": 2.7139375211970996e-05,
      "loss": 1.096,
      "step": 166
    },
    {
      "epoch": 9.41,
      "learning_rate": 2.6902155451277377e-05,
      "loss": 1.1161,
      "step": 167
    },
    {
      "epoch": 9.46,
      "learning_rate": 2.6664763299582602e-05,
      "loss": 1.1328,
      "step": 168
    },
    {
      "epoch": 9.52,
      "learning_rate": 2.6427220271569203e-05,
      "loss": 1.0747,
      "step": 169
    },
    {
      "epoch": 9.58,
      "learning_rate": 2.6189547895593562e-05,
      "loss": 1.1092,
      "step": 170
    },
    {
      "epoch": 9.63,
      "learning_rate": 2.5951767711734753e-05,
      "loss": 1.1624,
      "step": 171
    },
    {
      "epoch": 9.69,
      "learning_rate": 2.5713901269842404e-05,
      "loss": 1.1434,
      "step": 172
    },
    {
      "epoch": 9.75,
      "learning_rate": 2.5475970127583666e-05,
      "loss": 1.1167,
      "step": 173
    },
    {
      "epoch": 9.8,
      "learning_rate": 2.523799584848942e-05,
      "loss": 1.0509,
      "step": 174
    },
    {
      "epoch": 9.86,
      "learning_rate": 2.5e-05,
      "loss": 1.1449,
      "step": 175
    },
    {
      "epoch": 9.92,
      "learning_rate": 2.4762004151510584e-05,
      "loss": 1.109,
      "step": 176
    },
    {
      "epoch": 9.97,
      "learning_rate": 2.4524029872416333e-05,
      "loss": 1.0272,
      "step": 177
    },
    {
      "epoch": 10.03,
      "learning_rate": 2.42860987301576e-05,
      "loss": 1.1489,
      "step": 178
    },
    {
      "epoch": 10.08,
      "learning_rate": 2.4048232288265253e-05,
      "loss": 1.0263,
      "step": 179
    },
    {
      "epoch": 10.14,
      "learning_rate": 2.3810452104406444e-05,
      "loss": 1.0305,
      "step": 180
    },
    {
      "epoch": 10.2,
      "learning_rate": 2.35727797284308e-05,
      "loss": 0.9612,
      "step": 181
    },
    {
      "epoch": 10.25,
      "learning_rate": 2.3335236700417404e-05,
      "loss": 1.1883,
      "step": 182
    },
    {
      "epoch": 10.31,
      "learning_rate": 2.309784454872262e-05,
      "loss": 1.192,
      "step": 183
    },
    {
      "epoch": 10.37,
      "learning_rate": 2.2860624788029013e-05,
      "loss": 1.0919,
      "step": 184
    },
    {
      "epoch": 10.42,
      "learning_rate": 2.2623598917395438e-05,
      "loss": 1.0974,
      "step": 185
    },
    {
      "epoch": 10.48,
      "learning_rate": 2.238678841830867e-05,
      "loss": 1.0938,
      "step": 186
    },
    {
      "epoch": 10.54,
      "learning_rate": 2.2150214752736488e-05,
      "loss": 0.9879,
      "step": 187
    },
    {
      "epoch": 10.59,
      "learning_rate": 2.1913899361182632e-05,
      "loss": 1.0284,
      "step": 188
    },
    {
      "epoch": 10.65,
      "learning_rate": 2.167786366074365e-05,
      "loss": 1.0184,
      "step": 189
    },
    {
      "epoch": 10.7,
      "learning_rate": 2.1442129043167874e-05,
      "loss": 1.0419,
      "step": 190
    },
    {
      "epoch": 10.76,
      "learning_rate": 2.1206716872916714e-05,
      "loss": 1.0631,
      "step": 191
    },
    {
      "epoch": 10.82,
      "learning_rate": 2.09716484852284e-05,
      "loss": 1.0492,
      "step": 192
    },
    {
      "epoch": 10.87,
      "learning_rate": 2.0736945184184405e-05,
      "loss": 1.0924,
      "step": 193
    },
    {
      "epoch": 10.93,
      "learning_rate": 2.0502628240778655e-05,
      "loss": 0.9832,
      "step": 194
    },
    {
      "epoch": 10.99,
      "learning_rate": 2.0268718890989753e-05,
      "loss": 1.1266,
      "step": 195
    },
    {
      "epoch": 11.04,
      "learning_rate": 2.003523833385637e-05,
      "loss": 1.0762,
      "step": 196
    },
    {
      "epoch": 11.1,
      "learning_rate": 1.980220772955602e-05,
      "loss": 1.0011,
      "step": 197
    },
    {
      "epoch": 11.15,
      "learning_rate": 1.956964819748731e-05,
      "loss": 1.0195,
      "step": 198
    },
    {
      "epoch": 11.21,
      "learning_rate": 1.9337580814355888e-05,
      "loss": 1.0442,
      "step": 199
    },
    {
      "epoch": 11.27,
      "learning_rate": 1.9106026612264316e-05,
      "loss": 1.0285,
      "step": 200
    },
    {
      "epoch": 11.27,
      "eval_loss": 1.3292417526245117,
      "eval_runtime": 1.4356,
      "eval_samples_per_second": 6.966,
      "eval_steps_per_second": 3.483,
      "step": 200
    },
    {
      "epoch": 11.32,
      "learning_rate": 1.8875006576805914e-05,
      "loss": 0.9805,
      "step": 201
    },
    {
      "epoch": 11.38,
      "learning_rate": 1.8644541645162834e-05,
      "loss": 0.9562,
      "step": 202
    },
    {
      "epoch": 11.44,
      "learning_rate": 1.8414652704208583e-05,
      "loss": 1.0457,
      "step": 203
    },
    {
      "epoch": 11.49,
      "learning_rate": 1.8185360588615058e-05,
      "loss": 1.0217,
      "step": 204
    },
    {
      "epoch": 11.55,
      "learning_rate": 1.795668607896426e-05,
      "loss": 1.1281,
      "step": 205
    },
    {
      "epoch": 11.61,
      "learning_rate": 1.7728649899865024e-05,
      "loss": 0.9654,
      "step": 206
    },
    {
      "epoch": 11.66,
      "learning_rate": 1.7501272718074737e-05,
      "loss": 0.9011,
      "step": 207
    },
    {
      "epoch": 11.72,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 1.097,
      "step": 208
    },
    {
      "epoch": 11.77,
      "learning_rate": 1.7048577712960627e-05,
      "loss": 1.0652,
      "step": 209
    },
    {
      "epoch": 11.83,
      "learning_rate": 1.682330091706446e-05,
      "loss": 1.011,
      "step": 210
    },
    {
      "epoch": 11.89,
      "learning_rate": 1.6598765169614243e-05,
      "loss": 1.1001,
      "step": 211
    },
    {
      "epoch": 11.94,
      "learning_rate": 1.637499082012574e-05,
      "loss": 1.1224,
      "step": 212
    },
    {
      "epoch": 12.0,
      "learning_rate": 1.615199814910971e-05,
      "loss": 0.967,
      "step": 213
    },
    {
      "epoch": 12.06,
      "learning_rate": 1.5929807366233977e-05,
      "loss": 0.9923,
      "step": 214
    },
    {
      "epoch": 12.11,
      "learning_rate": 1.5708438608491814e-05,
      "loss": 1.0722,
      "step": 215
    },
    {
      "epoch": 12.17,
      "learning_rate": 1.5487911938376924e-05,
      "loss": 0.9666,
      "step": 216
    },
    {
      "epoch": 12.23,
      "learning_rate": 1.5268247342065215e-05,
      "loss": 0.9136,
      "step": 217
    },
    {
      "epoch": 12.28,
      "learning_rate": 1.5049464727603452e-05,
      "loss": 0.9274,
      "step": 218
    },
    {
      "epoch": 12.34,
      "learning_rate": 1.4831583923104999e-05,
      "loss": 1.0955,
      "step": 219
    },
    {
      "epoch": 12.39,
      "learning_rate": 1.4614624674952842e-05,
      "loss": 0.9058,
      "step": 220
    },
    {
      "epoch": 12.45,
      "learning_rate": 1.4398606646009963e-05,
      "loss": 0.8351,
      "step": 221
    },
    {
      "epoch": 12.51,
      "learning_rate": 1.4183549413837289e-05,
      "loss": 1.119,
      "step": 222
    },
    {
      "epoch": 12.56,
      "learning_rate": 1.3969472468919461e-05,
      "loss": 1.0418,
      "step": 223
    },
    {
      "epoch": 12.62,
      "learning_rate": 1.3756395212898359e-05,
      "loss": 0.9102,
      "step": 224
    },
    {
      "epoch": 12.68,
      "learning_rate": 1.354433695681474e-05,
      "loss": 0.997,
      "step": 225
    },
    {
      "epoch": 12.73,
      "learning_rate": 1.3333316919358157e-05,
      "loss": 1.1737,
      "step": 226
    },
    {
      "epoch": 12.79,
      "learning_rate": 1.3123354225125128e-05,
      "loss": 0.9887,
      "step": 227
    },
    {
      "epoch": 12.85,
      "learning_rate": 1.2914467902885901e-05,
      "loss": 0.9984,
      "step": 228
    },
    {
      "epoch": 12.9,
      "learning_rate": 1.2706676883859903e-05,
      "loss": 0.9507,
      "step": 229
    },
    {
      "epoch": 12.96,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.9395,
      "step": 230
    },
    {
      "epoch": 13.01,
      "learning_rate": 1.2294455982285777e-05,
      "loss": 1.1445,
      "step": 231
    },
    {
      "epoch": 13.07,
      "learning_rate": 1.2090063459025955e-05,
      "loss": 0.8469,
      "step": 232
    },
    {
      "epoch": 13.13,
      "learning_rate": 1.1886840954170142e-05,
      "loss": 0.9936,
      "step": 233
    },
    {
      "epoch": 13.18,
      "learning_rate": 1.1684806885630004e-05,
      "loss": 0.8797,
      "step": 234
    },
    {
      "epoch": 13.24,
      "learning_rate": 1.148397956361007e-05,
      "loss": 1.1331,
      "step": 235
    },
    {
      "epoch": 13.3,
      "learning_rate": 1.1284377188948258e-05,
      "loss": 0.9613,
      "step": 236
    },
    {
      "epoch": 13.35,
      "learning_rate": 1.1086017851466413e-05,
      "loss": 0.9343,
      "step": 237
    },
    {
      "epoch": 13.41,
      "learning_rate": 1.0888919528330777e-05,
      "loss": 1.0098,
      "step": 238
    },
    {
      "epoch": 13.46,
      "learning_rate": 1.0693100082422763e-05,
      "loss": 0.9669,
      "step": 239
    },
    {
      "epoch": 13.52,
      "learning_rate": 1.049857726072005e-05,
      "loss": 0.9686,
      "step": 240
    },
    {
      "epoch": 13.58,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.8916,
      "step": 241
    },
    {
      "epoch": 13.63,
      "learning_rate": 1.0113491888682802e-05,
      "loss": 0.9274,
      "step": 242
    },
    {
      "epoch": 13.69,
      "learning_rate": 9.922964238362762e-06,
      "loss": 0.9307,
      "step": 243
    },
    {
      "epoch": 13.75,
      "learning_rate": 9.733803009114045e-06,
      "loss": 1.0112,
      "step": 244
    },
    {
      "epoch": 13.8,
      "learning_rate": 9.546025344484869e-06,
      "loss": 1.0465,
      "step": 245
    },
    {
      "epoch": 13.86,
      "learning_rate": 9.359648262631961e-06,
      "loss": 1.0822,
      "step": 246
    },
    {
      "epoch": 13.92,
      "learning_rate": 9.174688654778243e-06,
      "loss": 0.8992,
      "step": 247
    },
    {
      "epoch": 13.97,
      "learning_rate": 8.991163283681944e-06,
      "loss": 0.8778,
      "step": 248
    },
    {
      "epoch": 14.03,
      "learning_rate": 8.809088782117452e-06,
      "loss": 1.0079,
      "step": 249
    },
    {
      "epoch": 14.08,
      "learning_rate": 8.628481651367876e-06,
      "loss": 0.9508,
      "step": 250
    },
    {
      "epoch": 14.14,
      "learning_rate": 8.449358259729537e-06,
      "loss": 0.997,
      "step": 251
    },
    {
      "epoch": 14.2,
      "learning_rate": 8.271734841028553e-06,
      "loss": 0.8669,
      "step": 252
    },
    {
      "epoch": 14.25,
      "learning_rate": 8.09562749314952e-06,
      "loss": 0.9721,
      "step": 253
    },
    {
      "epoch": 14.31,
      "learning_rate": 7.921052176576644e-06,
      "loss": 1.0777,
      "step": 254
    },
    {
      "epoch": 14.37,
      "learning_rate": 7.748024712947205e-06,
      "loss": 0.8644,
      "step": 255
    },
    {
      "epoch": 14.42,
      "learning_rate": 7.576560783617668e-06,
      "loss": 0.9119,
      "step": 256
    },
    {
      "epoch": 14.48,
      "learning_rate": 7.40667592824249e-06,
      "loss": 0.8645,
      "step": 257
    },
    {
      "epoch": 14.54,
      "learning_rate": 7.238385543365783e-06,
      "loss": 0.8786,
      "step": 258
    },
    {
      "epoch": 14.59,
      "learning_rate": 7.071704881025915e-06,
      "loss": 0.9539,
      "step": 259
    },
    {
      "epoch": 14.65,
      "learning_rate": 6.906649047373246e-06,
      "loss": 0.9521,
      "step": 260
    },
    {
      "epoch": 14.7,
      "learning_rate": 6.743233001301067e-06,
      "loss": 1.0708,
      "step": 261
    },
    {
      "epoch": 14.76,
      "learning_rate": 6.5814715530898745e-06,
      "loss": 1.033,
      "step": 262
    },
    {
      "epoch": 14.82,
      "learning_rate": 6.421379363065142e-06,
      "loss": 0.9344,
      "step": 263
    },
    {
      "epoch": 14.87,
      "learning_rate": 6.2629709402686535e-06,
      "loss": 0.9491,
      "step": 264
    },
    {
      "epoch": 14.93,
      "learning_rate": 6.106260641143546e-06,
      "loss": 0.8894,
      "step": 265
    },
    {
      "epoch": 14.99,
      "learning_rate": 5.951262668233232e-06,
      "loss": 0.8825,
      "step": 266
    },
    {
      "epoch": 15.04,
      "learning_rate": 5.797991068894201e-06,
      "loss": 0.925,
      "step": 267
    },
    {
      "epoch": 15.1,
      "learning_rate": 5.646459734022938e-06,
      "loss": 0.8431,
      "step": 268
    },
    {
      "epoch": 15.15,
      "learning_rate": 5.49668239679699e-06,
      "loss": 1.036,
      "step": 269
    },
    {
      "epoch": 15.21,
      "learning_rate": 5.348672631430318e-06,
      "loss": 0.9463,
      "step": 270
    },
    {
      "epoch": 15.27,
      "learning_rate": 5.202443851943126e-06,
      "loss": 0.9942,
      "step": 271
    },
    {
      "epoch": 15.32,
      "learning_rate": 5.058009310946119e-06,
      "loss": 0.9657,
      "step": 272
    },
    {
      "epoch": 15.38,
      "learning_rate": 4.915382098439436e-06,
      "loss": 0.9375,
      "step": 273
    },
    {
      "epoch": 15.44,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.9347,
      "step": 274
    },
    {
      "epoch": 15.49,
      "learning_rate": 4.6356011987416075e-06,
      "loss": 0.9796,
      "step": 275
    },
    {
      "epoch": 15.55,
      "learning_rate": 4.498472867895223e-06,
      "loss": 0.987,
      "step": 276
    },
    {
      "epoch": 15.61,
      "learning_rate": 4.36320257593065e-06,
      "loss": 0.8946,
      "step": 277
    },
    {
      "epoch": 15.66,
      "learning_rate": 4.229802582298633e-06,
      "loss": 0.9034,
      "step": 278
    },
    {
      "epoch": 15.72,
      "learning_rate": 4.098284976946101e-06,
      "loss": 1.0294,
      "step": 279
    },
    {
      "epoch": 15.77,
      "learning_rate": 3.968661679220468e-06,
      "loss": 0.9631,
      "step": 280
    },
    {
      "epoch": 15.83,
      "learning_rate": 3.840944436789393e-06,
      "loss": 0.8831,
      "step": 281
    },
    {
      "epoch": 15.89,
      "learning_rate": 3.715144824576078e-06,
      "loss": 0.9274,
      "step": 282
    },
    {
      "epoch": 15.94,
      "learning_rate": 3.591274243710277e-06,
      "loss": 0.8896,
      "step": 283
    },
    {
      "epoch": 16.0,
      "learning_rate": 3.4693439204949858e-06,
      "loss": 0.8672,
      "step": 284
    },
    {
      "epoch": 16.06,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.9043,
      "step": 285
    },
    {
      "epoch": 16.11,
      "learning_rate": 3.2313480720055745e-06,
      "loss": 1.1059,
      "step": 286
    },
    {
      "epoch": 16.17,
      "learning_rate": 3.1153041161266134e-06,
      "loss": 0.9241,
      "step": 287
    },
    {
      "epoch": 16.23,
      "learning_rate": 3.0012435547336737e-06,
      "loss": 0.7761,
      "step": 288
    },
    {
      "epoch": 16.28,
      "learning_rate": 2.889176725054643e-06,
      "loss": 1.0323,
      "step": 289
    },
    {
      "epoch": 16.34,
      "learning_rate": 2.779113783626916e-06,
      "loss": 0.8534,
      "step": 290
    },
    {
      "epoch": 16.39,
      "learning_rate": 2.671064705376905e-06,
      "loss": 0.7669,
      "step": 291
    },
    {
      "epoch": 16.45,
      "learning_rate": 2.565039282716045e-06,
      "loss": 0.984,
      "step": 292
    },
    {
      "epoch": 16.51,
      "learning_rate": 2.461047124653279e-06,
      "loss": 0.9542,
      "step": 293
    },
    {
      "epoch": 16.56,
      "learning_rate": 2.3590976559242278e-06,
      "loss": 0.9439,
      "step": 294
    },
    {
      "epoch": 16.62,
      "learning_rate": 2.2592001161370392e-06,
      "loss": 0.8776,
      "step": 295
    },
    {
      "epoch": 16.68,
      "learning_rate": 2.1613635589349756e-06,
      "loss": 0.9211,
      "step": 296
    },
    {
      "epoch": 16.73,
      "learning_rate": 2.0655968511759134e-06,
      "loss": 0.9145,
      "step": 297
    },
    {
      "epoch": 16.79,
      "learning_rate": 1.97190867212875e-06,
      "loss": 0.9481,
      "step": 298
    },
    {
      "epoch": 16.85,
      "learning_rate": 1.8803075126867715e-06,
      "loss": 0.9805,
      "step": 299
    },
    {
      "epoch": 16.9,
      "learning_rate": 1.790801674598186e-06,
      "loss": 0.8387,
      "step": 300
    },
    {
      "epoch": 16.9,
      "eval_loss": 1.3825798034667969,
      "eval_runtime": 1.4357,
      "eval_samples_per_second": 6.965,
      "eval_steps_per_second": 3.483,
      "step": 300
    },
    {
      "epoch": 16.96,
      "learning_rate": 1.703399269713693e-06,
      "loss": 1.005,
      "step": 301
    },
    {
      "epoch": 17.01,
      "learning_rate": 1.6181082192513353e-06,
      "loss": 0.9032,
      "step": 302
    },
    {
      "epoch": 17.07,
      "learning_rate": 1.534936253078606e-06,
      "loss": 1.0064,
      "step": 303
    },
    {
      "epoch": 17.13,
      "learning_rate": 1.4538909090118846e-06,
      "loss": 0.8834,
      "step": 304
    },
    {
      "epoch": 17.18,
      "learning_rate": 1.3749795321332887e-06,
      "loss": 0.93,
      "step": 305
    },
    {
      "epoch": 17.24,
      "learning_rate": 1.2982092741250145e-06,
      "loss": 0.9181,
      "step": 306
    },
    {
      "epoch": 17.3,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 0.8043,
      "step": 307
    },
    {
      "epoch": 17.35,
      "learning_rate": 1.1511197505771843e-06,
      "loss": 0.8552,
      "step": 308
    },
    {
      "epoch": 17.41,
      "learning_rate": 1.0808138156569614e-06,
      "loss": 0.8864,
      "step": 309
    },
    {
      "epoch": 17.46,
      "learning_rate": 1.0126756596375686e-06,
      "loss": 0.8856,
      "step": 310
    },
    {
      "epoch": 17.52,
      "learning_rate": 9.467114578318226e-07,
      "loss": 0.9447,
      "step": 311
    },
    {
      "epoch": 17.58,
      "learning_rate": 8.829271885286094e-07,
      "loss": 0.8091,
      "step": 312
    },
    {
      "epoch": 17.63,
      "learning_rate": 8.213286324510738e-07,
      "loss": 0.9956,
      "step": 313
    },
    {
      "epoch": 17.69,
      "learning_rate": 7.619213722327185e-07,
      "loss": 0.88,
      "step": 314
    },
    {
      "epoch": 17.75,
      "learning_rate": 7.047107919114588e-07,
      "loss": 0.9142,
      "step": 315
    },
    {
      "epoch": 17.8,
      "learning_rate": 6.497020764416633e-07,
      "loss": 0.9984,
      "step": 316
    },
    {
      "epoch": 17.86,
      "learning_rate": 5.969002112242494e-07,
      "loss": 0.8869,
      "step": 317
    },
    {
      "epoch": 17.92,
      "learning_rate": 5.463099816548579e-07,
      "loss": 0.9627,
      "step": 318
    },
    {
      "epoch": 17.97,
      "learning_rate": 4.979359726901639e-07,
      "loss": 0.9783,
      "step": 319
    },
    {
      "epoch": 18.03,
      "learning_rate": 4.517825684323324e-07,
      "loss": 1.0067,
      "step": 320
    },
    {
      "epoch": 18.08,
      "learning_rate": 4.078539517316987e-07,
      "loss": 0.9261,
      "step": 321
    },
    {
      "epoch": 18.14,
      "learning_rate": 3.6615410380767544e-07,
      "loss": 1.0504,
      "step": 322
    },
    {
      "epoch": 18.2,
      "learning_rate": 3.266868038879434e-07,
      "loss": 0.8995,
      "step": 323
    },
    {
      "epoch": 18.25,
      "learning_rate": 2.894556288659395e-07,
      "loss": 0.915,
      "step": 324
    },
    {
      "epoch": 18.31,
      "learning_rate": 2.544639529766829e-07,
      "loss": 0.8657,
      "step": 325
    },
    {
      "epoch": 18.37,
      "learning_rate": 2.2171494749097245e-07,
      "loss": 0.9171,
      "step": 326
    },
    {
      "epoch": 18.42,
      "learning_rate": 1.912115804279746e-07,
      "loss": 0.7903,
      "step": 327
    },
    {
      "epoch": 18.48,
      "learning_rate": 1.6295661628624447e-07,
      "loss": 0.9827,
      "step": 328
    },
    {
      "epoch": 18.54,
      "learning_rate": 1.3695261579316777e-07,
      "loss": 0.9373,
      "step": 329
    },
    {
      "epoch": 18.59,
      "learning_rate": 1.1320193567288529e-07,
      "loss": 0.915,
      "step": 330
    },
    {
      "epoch": 18.65,
      "learning_rate": 9.170672843271666e-08,
      "loss": 1.0085,
      "step": 331
    },
    {
      "epoch": 18.7,
      "learning_rate": 7.246894216806355e-08,
      "loss": 0.9681,
      "step": 332
    },
    {
      "epoch": 18.76,
      "learning_rate": 5.54903203858731e-08,
      "loss": 0.8392,
      "step": 333
    },
    {
      "epoch": 18.82,
      "learning_rate": 4.07724018466088e-08,
      "loss": 0.9473,
      "step": 334
    },
    {
      "epoch": 18.87,
      "learning_rate": 2.831652042480093e-08,
      "loss": 0.9534,
      "step": 335
    },
    {
      "epoch": 18.93,
      "learning_rate": 1.812380498815991e-08,
      "loss": 0.9152,
      "step": 336
    },
    {
      "epoch": 18.99,
      "learning_rate": 1.0195179295269252e-08,
      "loss": 0.8761,
      "step": 337
    },
    {
      "epoch": 19.04,
      "learning_rate": 4.531361911855325e-09,
      "loss": 0.9116,
      "step": 338
    },
    {
      "epoch": 19.1,
      "learning_rate": 1.132866145678313e-09,
      "loss": 0.9118,
      "step": 339
    },
    {
      "epoch": 19.15,
      "learning_rate": 0.0,
      "loss": 0.8806,
      "step": 340
    }
  ],
  "logging_steps": 1,
  "max_steps": 340,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 4.253890839379968e+17,
  "trial_name": null,
  "trial_params": null
}