{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8133333333333335,
  "global_step": 340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.9122,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 2.0707,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.9703,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.705882352941177e-05,
      "loss": 2.015,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.882352941176471e-05,
      "loss": 2.119,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.058823529411765e-05,
      "loss": 2.0515,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.23529411764706e-05,
      "loss": 1.7436,
      "step": 7
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.411764705882353e-05,
      "loss": 1.9326,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010588235294117647,
      "loss": 2.0819,
      "step": 9
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00011764705882352942,
      "loss": 1.9965,
      "step": 10
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012941176470588237,
      "loss": 2.0543,
      "step": 11
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001411764705882353,
      "loss": 2.0461,
      "step": 12
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00015294117647058822,
      "loss": 2.311,
      "step": 13
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001647058823529412,
      "loss": 1.8447,
      "step": 14
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00017647058823529413,
      "loss": 2.6263,
      "step": 15
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018823529411764707,
      "loss": 2.6179,
      "step": 16
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.535,
      "step": 17
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999833248118322,
      "loss": 2.5924,
      "step": 18
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999332998034514,
      "loss": 2.3562,
      "step": 19
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019998499266432108,
      "loss": 2.2352,
      "step": 20
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019997332081116373,
      "loss": 2.152,
      "step": 21
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019995831481013374,
      "loss": 2.1149,
      "step": 22
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019993997516168689,
      "loss": 2.1608,
      "step": 23
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001999183024774573,
      "loss": 2.1593,
      "step": 24
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019989329748023725,
      "loss": 2.2774,
      "step": 25
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019986496100395275,
      "loss": 2.0355,
      "step": 26
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019983329399363598,
      "loss": 1.9455,
      "step": 27
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001997982975053936,
      "loss": 2.5648,
      "step": 28
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001997599727063717,
      "loss": 2.3619,
      "step": 29
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019971832087471676,
      "loss": 2.0888,
      "step": 30
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000199673343399533,
      "loss": 1.9363,
      "step": 31
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019962504178083618,
      "loss": 2.0259,
      "step": 32
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019957341762950344,
      "loss": 1.8482,
      "step": 33
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001995184726672197,
      "loss": 1.8542,
      "step": 34
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001994602087264201,
      "loss": 1.9435,
      "step": 35
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019939862775022893,
      "loss": 1.6559,
      "step": 36
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019933373179239502,
      "loss": 1.9478,
      "step": 37
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001992655230172229,
      "loss": 1.9417,
      "step": 38
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000199194003699501,
      "loss": 1.9067,
      "step": 39
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019911917622442537,
      "loss": 1.6106,
      "step": 40
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001990410430875205,
      "loss": 1.2742,
      "step": 41
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019895960689455598,
      "loss": 1.3048,
      "step": 42
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001988748703614594,
      "loss": 1.1847,
      "step": 43
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019878683631422605,
      "loss": 1.1683,
      "step": 44
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019869550768882455,
      "loss": 1.1531,
      "step": 45
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019860088753109896,
      "loss": 1.1401,
      "step": 46
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001985029789966671,
      "loss": 1.8959,
      "step": 47
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019840178535081545,
      "loss": 1.897,
      "step": 48
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001982973099683902,
      "loss": 1.791,
      "step": 49
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019818955633368464,
      "loss": 1.7451,
      "step": 50
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019807852804032305,
      "loss": 1.8556,
      "step": 51
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019796422879114084,
      "loss": 1.7882,
      "step": 52
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001978466623980609,
      "loss": 1.8834,
      "step": 53
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019772583278196678,
      "loss": 1.7593,
      "step": 54
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019760174397257156,
      "loss": 1.8291,
      "step": 55
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019747440010828383,
      "loss": 1.808,
      "step": 56
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001973438054360693,
      "loss": 1.6324,
      "step": 57
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019720996431130946,
      "loss": 1.483,
      "step": 58
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019707288119765623,
      "loss": 1.9648,
      "step": 59
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000196932560666883,
      "loss": 1.5742,
      "step": 60
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019678900739873226,
      "loss": 1.7066,
      "step": 61
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019664222618075958,
      "loss": 2.0719,
      "step": 62
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001964922219081738,
      "loss": 1.9432,
      "step": 63
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019633899958367384,
      "loss": 1.7979,
      "step": 64
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019618256431728194,
      "loss": 1.6286,
      "step": 65
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000196022921326173,
      "loss": 1.6031,
      "step": 66
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019586007593450097,
      "loss": 1.5169,
      "step": 67
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001956940335732209,
      "loss": 1.5923,
      "step": 68
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000195524799779908,
      "loss": 1.6123,
      "step": 69
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000195352380198573,
      "loss": 1.7392,
      "step": 70
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019517678057947384,
      "loss": 1.6406,
      "step": 71
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019499800677892385,
      "loss": 1.5532,
      "step": 72
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001948160647590966,
      "loss": 1.816,
      "step": 73
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001946309605878269,
      "loss": 1.5759,
      "step": 74
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019444270043840852,
      "loss": 1.6726,
      "step": 75
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019425129058938832,
      "loss": 1.6134,
      "step": 76
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019405673742435678,
      "loss": 1.6285,
      "step": 77
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019385904743173516,
      "loss": 1.6023,
      "step": 78
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019365822720455916,
      "loss": 1.5177,
      "step": 79
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019345428344025883,
      "loss": 1.5413,
      "step": 80
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019324722294043558,
      "loss": 1.3404,
      "step": 81
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019303705261063497,
      "loss": 1.6409,
      "step": 82
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019282377946011652,
      "loss": 1.6361,
      "step": 83
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019260741060162016,
      "loss": 1.4902,
      "step": 84
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001923879532511287,
      "loss": 1.3232,
      "step": 85
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019216541472762735,
      "loss": 1.2438,
      "step": 86
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019193980245285966,
      "loss": 1.0828,
      "step": 87
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019171112395107985,
      "loss": 1.0696,
      "step": 88
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001914793868488021,
      "loss": 1.0179,
      "step": 89
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001912445988745459,
      "loss": 1.0012,
      "step": 90
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001910067678585786,
      "loss": 0.9423,
      "step": 91
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019076590173265406,
      "loss": 0.9173,
      "step": 92
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019052200852974819,
      "loss": 1.8901,
      "step": 93
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001902750963837912,
      "loss": 1.9665,
      "step": 94
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019002517352939598,
      "loss": 1.8323,
      "step": 95
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001897722483015838,
      "loss": 1.7828,
      "step": 96
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018951632913550626,
      "loss": 1.5083,
      "step": 97
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018925742456616374,
      "loss": 1.6924,
      "step": 98
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001889955432281212,
      "loss": 1.7446,
      "step": 99
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001887306938552197,
      "loss": 1.6143,
      "step": 100
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018846288528028555,
      "loss": 1.5013,
      "step": 101
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001881921264348355,
      "loss": 1.6335,
      "step": 102
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018791842634877898,
      "loss": 1.5852,
      "step": 103
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018764179415011682,
      "loss": 1.4358,
      "step": 104
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018736223906463696,
      "loss": 1.7103,
      "step": 105
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001870797704156067,
      "loss": 1.3361,
      "step": 106
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018679439762346185,
      "loss": 1.7021,
      "step": 107
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018650613020549232,
      "loss": 2.3076,
      "step": 108
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018621497777552507,
      "loss": 1.6109,
      "step": 109
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018592095004360318,
      "loss": 1.8032,
      "step": 110
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018562405681566216,
      "loss": 1.6432,
      "step": 111
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001853243079932029,
      "loss": 1.4159,
      "step": 112
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018502171357296144,
      "loss": 1.4869,
      "step": 113
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018471628364657555,
      "loss": 1.419,
      "step": 114
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018440802840024822,
      "loss": 1.3616,
      "step": 115
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018409695811440796,
      "loss": 1.4805,
      "step": 116
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018378308316336584,
      "loss": 1.5585,
      "step": 117
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001834664140149696,
      "loss": 1.4302,
      "step": 118
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018314696123025454,
      "loss": 1.3596,
      "step": 119
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001828247354630912,
      "loss": 1.5605,
      "step": 120
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018249974745983023,
      "loss": 1.5355,
      "step": 121
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018217200805894384,
      "loss": 1.5559,
      "step": 122
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018184152819066435,
      "loss": 1.3455,
      "step": 123
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018150831887661978,
      "loss": 1.4451,
      "step": 124
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018117239122946615,
      "loss": 1.302,
      "step": 125
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018083375645251684,
      "loss": 1.2725,
      "step": 126
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001804924258393692,
      "loss": 1.2186,
      "step": 127
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00018014841077352762,
      "loss": 1.2388,
      "step": 128
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000179801722728024,
      "loss": 1.2655,
      "step": 129
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00017945237326503507,
      "loss": 1.1938,
      "step": 130
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017910037403549693,
      "loss": 1.1203,
      "step": 131
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001787457367787164,
      "loss": 1.1576,
      "step": 132
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017838847332197938,
      "loss": 1.0116,
      "step": 133
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017802859558015664,
      "loss": 0.8979,
      "step": 134
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017766611555530636,
      "loss": 0.8594,
      "step": 135
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001773010453362737,
      "loss": 0.819,
      "step": 136
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00017693339709828792,
      "loss": 0.8788,
      "step": 137
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017656318310255604,
      "loss": 0.8013,
      "step": 138
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017619041569585418,
      "loss": 1.6861,
      "step": 139
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001758151073101157,
      "loss": 1.6799,
      "step": 140
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001754372704620164,
      "loss": 1.7259,
      "step": 141
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017505691775255745,
      "loss": 1.6804,
      "step": 142
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017467406186664474,
      "loss": 1.6242,
      "step": 143
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001742887155726663,
      "loss": 1.7912,
      "step": 144
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017390089172206592,
      "loss": 1.5403,
      "step": 145
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017351060324891502,
      "loss": 1.5285,
      "step": 146
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001731178631694811,
      "loss": 1.5643,
      "step": 147
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00017272268458179353,
      "loss": 1.425,
      "step": 148
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00017232508066520702,
      "loss": 1.4601,
      "step": 149
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017192506467996174,
      "loss": 1.3357,
      "step": 150
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017152264996674136,
      "loss": 1.6524,
      "step": 151
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017111784994622804,
      "loss": 1.181,
      "step": 152
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.7122,
      "step": 153
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00017030114806335526,
      "loss": 2.103,
      "step": 154
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016988927343831095,
      "loss": 1.5937,
      "step": 155
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016947506797969562,
      "loss": 1.5736,
      "step": 156
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016905854550141716,
      "loss": 1.2724,
      "step": 157
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016863971989465698,
      "loss": 1.224,
      "step": 158
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00016821860512740671,
      "loss": 1.1956,
      "step": 159
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00016779521524400232,
      "loss": 1.2721,
      "step": 160
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016736956436465573,
      "loss": 1.3703,
      "step": 161
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016694166668498398,
      "loss": 1.2,
      "step": 162
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016651153647553567,
      "loss": 1.031,
      "step": 163
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016607918808131525,
      "loss": 1.1153,
      "step": 164
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016564463592130428,
      "loss": 1.4222,
      "step": 165
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016520789448798087,
      "loss": 1.1901,
      "step": 166
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001647689783468362,
      "loss": 1.278,
      "step": 167
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016432790213588872,
      "loss": 1.3186,
      "step": 168
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016388468056519612,
      "loss": 1.1945,
      "step": 169
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016343932841636456,
      "loss": 1.1583,
      "step": 170
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016299186054205577,
      "loss": 1.0005,
      "step": 171
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001625422918654918,
      "loss": 0.9833,
      "step": 172
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016209063737995715,
      "loss": 1.0031,
      "step": 173
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016163691214829892,
      "loss": 0.9844,
      "step": 174
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016118113130242432,
      "loss": 0.9744,
      "step": 175
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00016072331004279614,
      "loss": 1.025,
      "step": 176
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00016026346363792567,
      "loss": 0.869,
      "step": 177
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001598016074238635,
      "loss": 0.8968,
      "step": 178
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015933775680368822,
      "loss": 0.8441,
      "step": 179
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001588719272469926,
      "loss": 0.767,
      "step": 180
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015840413428936767,
      "loss": 0.5753,
      "step": 181
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001579343935318846,
      "loss": 0.6553,
      "step": 182
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001574627206405744,
      "loss": 0.6268,
      "step": 183
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015698913134590552,
      "loss": 0.5677,
      "step": 184
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001565136414422592,
      "loss": 1.4827,
      "step": 185
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015603626678740263,
      "loss": 1.4317,
      "step": 186
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.9108,
      "step": 187
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015507592696888258,
      "loss": 1.19,
      "step": 188
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015459299383291345,
      "loss": 1.7435,
      "step": 189
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015410824000005468,
      "loss": 1.5147,
      "step": 190
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.000153621681637029,
      "loss": 1.7445,
      "step": 191
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001531333349707409,
      "loss": 1.5158,
      "step": 192
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001526432162877356,
      "loss": 1.6239,
      "step": 193
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001521513419336555,
      "loss": 1.4444,
      "step": 194
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00015165772831269547,
      "loss": 1.5048,
      "step": 195
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00015116239188705556,
      "loss": 1.5457,
      "step": 196
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00015066534917639195,
      "loss": 1.4051,
      "step": 197
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00015016661675726608,
      "loss": 1.2748,
      "step": 198
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014966621126259183,
      "loss": 1.3219,
      "step": 199
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001491641493810808,
      "loss": 1.1541,
      "step": 200
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014866044785668563,
      "loss": 1.4747,
      "step": 201
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014815512348804178,
      "loss": 1.1666,
      "step": 202
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014764819312790707,
      "loss": 1.2449,
      "step": 203
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001471396736825998,
      "loss": 1.8251,
      "step": 204
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001466295821114348,
      "loss": 1.2484,
      "step": 205
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014611793542615803,
      "loss": 1.4197,
      "step": 206
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014560475069037894,
      "loss": 1.2089,
      "step": 207
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001450900450190016,
      "loss": 1.0404,
      "step": 208
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014457383557765386,
      "loss": 1.0625,
      "step": 209
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014405613958211482,
      "loss": 0.947,
      "step": 210
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014353697429774084,
      "loss": 1.1545,
      "step": 211
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014301635703888943,
      "loss": 1.0116,
      "step": 212
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001424943051683422,
      "loss": 0.8152,
      "step": 213
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00014197083609672543,
      "loss": 0.8963,
      "step": 214
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001414459672819297,
      "loss": 1.3162,
      "step": 215
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001409197162285275,
      "loss": 0.8569,
      "step": 216
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00014039210048718949,
      "loss": 1.171,
      "step": 217
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013986313765409925,
      "loss": 0.8849,
      "step": 218
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013933284537036625,
      "loss": 0.9212,
      "step": 219
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013880124132143782,
      "loss": 0.7478,
      "step": 220
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.000138268343236509,
      "loss": 0.6915,
      "step": 221
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013773416888793145,
      "loss": 0.6634,
      "step": 222
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013719873609062077,
      "loss": 0.7808,
      "step": 223
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013666206270146223,
      "loss": 0.7653,
      "step": 224
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013612416661871533,
      "loss": 0.6742,
      "step": 225
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013558506578141682,
      "loss": 0.7197,
      "step": 226
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001350447781687826,
      "loss": 0.5688,
      "step": 227
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001345033217996078,
      "loss": 0.5976,
      "step": 228
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013396071473166613,
      "loss": 0.5635,
      "step": 229
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00013341697506110754,
      "loss": 0.4534,
      "step": 230
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00013287212092185464,
      "loss": 0.455,
      "step": 231
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.000132326170484998,
      "loss": 0.4934,
      "step": 232
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00013177914195819016,
      "loss": 0.4047,
      "step": 233
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001312310535850384,
      "loss": 0.9632,
      "step": 234
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00013068192364449618,
      "loss": 1.5302,
      "step": 235
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00013013177045025374,
      "loss": 1.5886,
      "step": 236
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012958061235012706,
      "loss": 1.5665,
      "step": 237
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012902846772544624,
      "loss": 1.3943,
      "step": 238
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001284753549904423,
      "loss": 1.3516,
      "step": 239
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012792129259163318,
      "loss": 1.5157,
      "step": 240
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001273662990072083,
      "loss": 1.4044,
      "step": 241
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001268103927464126,
      "loss": 1.4095,
      "step": 242
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012625359234892907,
      "loss": 1.3318,
      "step": 243
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012569591638426052,
      "loss": 1.1496,
      "step": 244
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001251373834511103,
      "loss": 1.2188,
      "step": 245
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012457801217676182,
      "loss": 1.3083,
      "step": 246
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012401782121645766,
      "loss": 1.1114,
      "step": 247
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012345682925277716,
      "loss": 1.1415,
      "step": 248
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001228950549950134,
      "loss": 1.8205,
      "step": 249
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00012233251717854937,
      "loss": 1.2441,
      "step": 250
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00012176923456423284,
      "loss": 1.2625,
      "step": 251
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00012120522593775108,
      "loss": 1.1744,
      "step": 252
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00012064051010900397,
      "loss": 0.9422,
      "step": 253
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00012007510591147697,
      "loss": 0.9428,
      "step": 254
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.9575,
      "step": 255
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011894230785818284,
      "loss": 0.8955,
      "step": 256
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011837495178165706,
      "loss": 0.9415,
      "step": 257
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011780698289357419,
      "loss": 0.7821,
      "step": 258
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011723842013591044,
      "loss": 0.7817,
      "step": 259
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011666928247044768,
      "loss": 0.7947,
      "step": 260
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011609958887814129,
      "loss": 1.0891,
      "step": 261
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011552935835848697,
      "loss": 0.7932,
      "step": 262
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011495860992888712,
      "loss": 1.0385,
      "step": 263
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011438736262401669,
      "loss": 0.7126,
      "step": 264
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011381563549518823,
      "loss": 0.7194,
      "step": 265
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011324344760971671,
      "loss": 0.6358,
      "step": 266
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011267081805028339,
      "loss": 0.513,
      "step": 267
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00011209776591429962,
      "loss": 0.5445,
      "step": 268
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00011152431031326978,
      "loss": 0.6362,
      "step": 269
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00011095047037215396,
      "loss": 0.6582,
      "step": 270
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00011037626522873019,
      "loss": 0.5072,
      "step": 271
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001098017140329561,
      "loss": 0.568,
      "step": 272
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010922683594633021,
      "loss": 0.5671,
      "step": 273
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010865165014125316,
      "loss": 0.5759,
      "step": 274
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010807617580038796,
      "loss": 0.4984,
      "step": 275
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010750043211602045,
      "loss": 0.435,
      "step": 276
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010692443828941918,
      "loss": 0.4135,
      "step": 277
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010634821353019504,
      "loss": 0.3939,
      "step": 278
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010577177705566061,
      "loss": 0.3891,
      "step": 279
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010519514809018927,
      "loss": 0.8678,
      "step": 280
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010461834586457398,
      "loss": 1.5705,
      "step": 281
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010404138961538603,
      "loss": 1.7109,
      "step": 282
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010346429858433352,
      "loss": 1.271,
      "step": 283
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010288709201761948,
      "loss": 1.2667,
      "step": 284
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00010230978916530012,
      "loss": 1.4117,
      "step": 285
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00010173240928064285,
      "loss": 1.4835,
      "step": 286
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00010115497161948409,
      "loss": 1.2376,
      "step": 287
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00010057749543958717,
      "loss": 1.3616,
      "step": 288
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001,
      "loss": 1.1731,
      "step": 289
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.942250456041286e-05,
      "loss": 1.2436,
      "step": 290
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.884502838051595e-05,
      "loss": 1.1019,
      "step": 291
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.826759071935718e-05,
      "loss": 1.2143,
      "step": 292
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.76902108346999e-05,
      "loss": 0.8841,
      "step": 293
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.711290798238057e-05,
      "loss": 1.075,
      "step": 294
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.653570141566653e-05,
      "loss": 1.5949,
      "step": 295
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.595861038461398e-05,
      "loss": 1.0204,
      "step": 296
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.538165413542607e-05,
      "loss": 1.1104,
      "step": 297
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.480485190981073e-05,
      "loss": 1.0312,
      "step": 298
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.422822294433939e-05,
      "loss": 0.8481,
      "step": 299
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.365178646980497e-05,
      "loss": 0.8279,
      "step": 300
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.307556171058085e-05,
      "loss": 0.768,
      "step": 301
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.249956788397957e-05,
      "loss": 0.794,
      "step": 302
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.192382419961208e-05,
      "loss": 0.8737,
      "step": 303
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.134834985874688e-05,
      "loss": 1.0419,
      "step": 304
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.077316405366981e-05,
      "loss": 0.6576,
      "step": 305
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.019828596704394e-05,
      "loss": 0.4765,
      "step": 306
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.962373477126983e-05,
      "loss": 0.8899,
      "step": 307
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.904952962784605e-05,
      "loss": 0.7921,
      "step": 308
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.847568968673026e-05,
      "loss": 0.8791,
      "step": 309
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.790223408570042e-05,
      "loss": 0.811,
      "step": 310
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.732918194971664e-05,
      "loss": 0.6333,
      "step": 311
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.675655239028333e-05,
      "loss": 0.5666,
      "step": 312
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.61843645048118e-05,
      "loss": 0.3983,
      "step": 313
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.561263737598338e-05,
      "loss": 0.3781,
      "step": 314
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.504139007111289e-05,
      "loss": 0.5553,
      "step": 315
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.447064164151304e-05,
      "loss": 0.5327,
      "step": 316
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.39004111218587e-05,
      "loss": 0.4589,
      "step": 317
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.333071752955233e-05,
      "loss": 0.4377,
      "step": 318
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.27615798640896e-05,
      "loss": 0.4125,
      "step": 319
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.219301710642583e-05,
      "loss": 0.4413,
      "step": 320
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.162504821834295e-05,
      "loss": 0.4931,
      "step": 321
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.10576921418172e-05,
      "loss": 0.4238,
      "step": 322
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.3512,
      "step": 323
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.992489408852306e-05,
      "loss": 0.3913,
      "step": 324
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.935948989099605e-05,
      "loss": 0.3857,
      "step": 325
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.879477406224894e-05,
      "loss": 0.8727,
      "step": 326
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.823076543576717e-05,
      "loss": 1.2647,
      "step": 327
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.766748282145068e-05,
      "loss": 1.4902,
      "step": 328
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.710494500498662e-05,
      "loss": 1.4818,
      "step": 329
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.654317074722287e-05,
      "loss": 1.54,
      "step": 330
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.598217878354237e-05,
      "loss": 1.4253,
      "step": 331
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.542198782323819e-05,
      "loss": 1.2916,
      "step": 332
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.486261654888973e-05,
      "loss": 1.2685,
      "step": 333
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.430408361573948e-05,
      "loss": 1.1558,
      "step": 334
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.374640765107095e-05,
      "loss": 1.0571,
      "step": 335
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.318960725358741e-05,
      "loss": 1.1138,
      "step": 336
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.263370099279172e-05,
      "loss": 0.9725,
      "step": 337
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.207870740836684e-05,
      "loss": 1.1059,
      "step": 338
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.152464500955769e-05,
      "loss": 0.8638,
      "step": 339
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.097153227455379e-05,
      "loss": 1.0556,
      "step": 340
    }
  ],
  "max_steps": 561,
  "num_train_epochs": 3,
  "total_flos": 6.3420441403392e+16,
  "trial_name": null,
  "trial_params": null
}