{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 209,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.9497,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.9195,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.5914,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.0225,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014285714285714287,
      "loss": 0.9275,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017142857142857143,
      "loss": 0.943,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.8914,
      "step": 7
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019998790632601496,
      "loss": 0.8295,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019995162822919883,
      "loss": 0.8305,
      "step": 9
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019989117448426108,
      "loss": 0.8282,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019980655971335945,
      "loss": 0.8169,
      "step": 11
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019969780438256293,
      "loss": 0.872,
      "step": 12
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001995649347969019,
      "loss": 0.8213,
      "step": 13
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019940798309400526,
      "loss": 0.8319,
      "step": 14
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019922698723632767,
      "loss": 0.8022,
      "step": 15
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019902199100196697,
      "loss": 0.8143,
      "step": 16
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001987930439740757,
      "loss": 0.7737,
      "step": 17
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019854020152886814,
      "loss": 0.77,
      "step": 18
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019826352482222638,
      "loss": 0.7734,
      "step": 19
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019796308077490817,
      "loss": 0.7595,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019763894205636072,
      "loss": 0.7406,
      "step": 21
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019729118706714375,
      "loss": 0.7815,
      "step": 22
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019691989991996663,
      "loss": 0.7846,
      "step": 23
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019652517041934356,
      "loss": 0.7738,
      "step": 24
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019610709403987246,
      "loss": 0.7705,
      "step": 25
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019566577190314197,
      "loss": 0.7679,
      "step": 26
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019520131075327298,
      "loss": 0.745,
      "step": 27
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019471382293110003,
      "loss": 0.7201,
      "step": 28
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001942034263469989,
      "loss": 0.7607,
      "step": 29
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019367024445236754,
      "loss": 0.7435,
      "step": 30
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019311440620976597,
      "loss": 0.7471,
      "step": 31
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019253604606172417,
      "loss": 0.7379,
      "step": 32
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019193530389822363,
      "loss": 0.7338,
      "step": 33
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019131232502286188,
      "loss": 0.7215,
      "step": 34
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019066726011770726,
      "loss": 0.7112,
      "step": 35
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019000026520685302,
      "loss": 0.7532,
      "step": 36
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018931150161867916,
      "loss": 0.7255,
      "step": 37
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018860113594683148,
      "loss": 0.6952,
      "step": 38
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018786934000992688,
      "loss": 0.7078,
      "step": 39
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018711629080999504,
      "loss": 0.7591,
      "step": 40
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018634217048966637,
      "loss": 0.7633,
      "step": 41
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001855471662881164,
      "loss": 0.7734,
      "step": 42
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018473147049577774,
      "loss": 0.7339,
      "step": 43
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018389528040783012,
      "loss": 0.7405,
      "step": 44
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018303879827647975,
      "loss": 0.7105,
      "step": 45
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018216223126204007,
      "loss": 0.6787,
      "step": 46
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018126579138282503,
      "loss": 0.7194,
      "step": 47
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018034969546386757,
      "loss": 0.719,
      "step": 48
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017941416508447536,
      "loss": 0.7252,
      "step": 49
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001784594265246366,
      "loss": 0.7622,
      "step": 50
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000177485710710289,
      "loss": 0.7449,
      "step": 51
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017649325315746478,
      "loss": 0.7501,
      "step": 52
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017548229391532572,
      "loss": 0.726,
      "step": 53
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001744530775081015,
      "loss": 0.7256,
      "step": 54
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017340585287594604,
      "loss": 0.7262,
      "step": 55
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017234087331472497,
      "loss": 0.6974,
      "step": 56
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017125839641475072,
      "loss": 0.7005,
      "step": 57
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017015868399847768,
      "loss": 0.6988,
      "step": 58
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001690420020571747,
      "loss": 0.7421,
      "step": 59
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001679086206865886,
      "loss": 0.7025,
      "step": 60
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016675881402161536,
      "loss": 0.6785,
      "step": 61
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000165592860169994,
      "loss": 0.737,
      "step": 62
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001644110411450398,
      "loss": 0.6967,
      "step": 63
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016321364279743266,
      "loss": 0.6779,
      "step": 64
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016200095474607753,
      "loss": 0.7232,
      "step": 65
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001607732703080532,
      "loss": 0.6968,
      "step": 66
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001595308864276666,
      "loss": 0.6762,
      "step": 67
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001582741036046301,
      "loss": 0.7105,
      "step": 68
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015700322582137827,
      "loss": 0.7085,
      "step": 69
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015571856046954285,
      "loss": 0.7015,
      "step": 70
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015442041827560274,
      "loss": 0.7298,
      "step": 71
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015310911322572753,
      "loss": 0.7309,
      "step": 72
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015178496248983254,
      "loss": 0.6814,
      "step": 73
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000150448286344864,
      "loss": 0.7037,
      "step": 74
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014909940809733222,
      "loss": 0.7127,
      "step": 75
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014773865400511272,
      "loss": 0.7027,
      "step": 76
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014636635319853275,
      "loss": 0.7314,
      "step": 77
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001449828376007636,
      "loss": 0.6901,
      "step": 78
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014358844184753712,
      "loss": 0.7443,
      "step": 79
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014218350320620624,
      "loss": 0.7472,
      "step": 80
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014076836149416887,
      "loss": 0.6895,
      "step": 81
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013934335899667527,
      "loss": 0.6951,
      "step": 82
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013790884038403795,
      "loss": 0.6848,
      "step": 83
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013646515262826552,
      "loss": 0.6968,
      "step": 84
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013501264491913906,
      "loss": 0.7096,
      "step": 85
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001335516685797525,
      "loss": 0.7127,
      "step": 86
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013208257698153677,
      "loss": 0.712,
      "step": 87
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013060572545878875,
      "loss": 0.7116,
      "step": 88
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012912147122272523,
      "loss": 0.7233,
      "step": 89
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012763017327508305,
      "loss": 0.6696,
      "step": 90
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012613219232128608,
      "loss": 0.6935,
      "step": 91
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012462789068320017,
      "loss": 0.6739,
      "step": 92
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000123117632211497,
      "loss": 0.6716,
      "step": 93
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012160178219764837,
      "loss": 0.6942,
      "step": 94
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012008070728557186,
      "loss": 0.7181,
      "step": 95
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011855477538294935,
      "loss": 0.6918,
      "step": 96
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011702435557223987,
      "loss": 0.6572,
      "step": 97
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011548981802140848,
      "loss": 0.721,
      "step": 98
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011395153389439233,
      "loss": 0.7066,
      "step": 99
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011240987526132594,
      "loss": 0.6858,
      "step": 100
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011086521500854745,
      "loss": 0.6825,
      "step": 101
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010931792674840718,
      "loss": 0.7197,
      "step": 102
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010776838472890065,
      "loss": 0.6736,
      "step": 103
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010621696374314807,
      "loss": 0.6957,
      "step": 104
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010466403903874176,
      "loss": 0.7069,
      "step": 105
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001031099862269837,
      "loss": 0.7207,
      "step": 106
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001015551811920351,
      "loss": 0.6608,
      "step": 107
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 0.7013,
      "step": 108
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.844481880796491e-05,
      "loss": 0.6616,
      "step": 109
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.689001377301633e-05,
      "loss": 0.6875,
      "step": 110
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.533596096125825e-05,
      "loss": 0.6784,
      "step": 111
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.378303625685195e-05,
      "loss": 0.686,
      "step": 112
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.223161527109937e-05,
      "loss": 0.6517,
      "step": 113
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.068207325159284e-05,
      "loss": 0.6501,
      "step": 114
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.913478499145254e-05,
      "loss": 0.6608,
      "step": 115
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.759012473867407e-05,
      "loss": 0.6725,
      "step": 116
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.604846610560771e-05,
      "loss": 0.6768,
      "step": 117
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.451018197859153e-05,
      "loss": 0.6642,
      "step": 118
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.297564442776014e-05,
      "loss": 0.6709,
      "step": 119
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.144522461705067e-05,
      "loss": 0.6456,
      "step": 120
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.991929271442817e-05,
      "loss": 0.6621,
      "step": 121
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.839821780235168e-05,
      "loss": 0.682,
      "step": 122
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.688236778850306e-05,
      "loss": 0.6661,
      "step": 123
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.537210931679987e-05,
      "loss": 0.6728,
      "step": 124
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.386780767871397e-05,
      "loss": 0.6545,
      "step": 125
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.236982672491698e-05,
      "loss": 0.6743,
      "step": 126
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.087852877727481e-05,
      "loss": 0.7238,
      "step": 127
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.939427454121128e-05,
      "loss": 0.6373,
      "step": 128
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.791742301846326e-05,
      "loss": 0.6667,
      "step": 129
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.644833142024751e-05,
      "loss": 0.6869,
      "step": 130
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.498735508086093e-05,
      "loss": 0.697,
      "step": 131
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.35348473717345e-05,
      "loss": 0.6993,
      "step": 132
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.209115961596208e-05,
      "loss": 0.6749,
      "step": 133
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.065664100332478e-05,
      "loss": 0.655,
      "step": 134
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.923163850583113e-05,
      "loss": 0.6437,
      "step": 135
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.781649679379378e-05,
      "loss": 0.6566,
      "step": 136
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.6411558152462894e-05,
      "loss": 0.6552,
      "step": 137
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.501716239923642e-05,
      "loss": 0.6497,
      "step": 138
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.363364680146725e-05,
      "loss": 0.7142,
      "step": 139
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.226134599488728e-05,
      "loss": 0.6902,
      "step": 140
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.090059190266779e-05,
      "loss": 0.6649,
      "step": 141
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.955171365513603e-05,
      "loss": 0.6655,
      "step": 142
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.821503751016746e-05,
      "loss": 0.67,
      "step": 143
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.689088677427248e-05,
      "loss": 0.6632,
      "step": 144
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.5579581724397255e-05,
      "loss": 0.664,
      "step": 145
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.428143953045717e-05,
      "loss": 0.6463,
      "step": 146
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.2996774178621736e-05,
      "loss": 0.6417,
      "step": 147
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.172589639536991e-05,
      "loss": 0.6762,
      "step": 148
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.046911357233343e-05,
      "loss": 0.6431,
      "step": 149
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.922672969194686e-05,
      "loss": 0.6606,
      "step": 150
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.79990452539225e-05,
      "loss": 0.6919,
      "step": 151
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.678635720256737e-05,
      "loss": 0.6315,
      "step": 152
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.558895885496023e-05,
      "loss": 0.6572,
      "step": 153
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.440713983000601e-05,
      "loss": 0.6886,
      "step": 154
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.324118597838464e-05,
      "loss": 0.6411,
      "step": 155
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.209137931341143e-05,
      "loss": 0.6366,
      "step": 156
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0957997942825336e-05,
      "loss": 0.6311,
      "step": 157
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9841316001522347e-05,
      "loss": 0.6522,
      "step": 158
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.874160358524931e-05,
      "loss": 0.6575,
      "step": 159
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7659126685275027e-05,
      "loss": 0.6474,
      "step": 160
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.659414712405398e-05,
      "loss": 0.6441,
      "step": 161
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5546922491898495e-05,
      "loss": 0.6471,
      "step": 162
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.451770608467432e-05,
      "loss": 0.6659,
      "step": 163
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3506746842535242e-05,
      "loss": 0.6606,
      "step": 164
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.251428928971102e-05,
      "loss": 0.6227,
      "step": 165
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1540573475363402e-05,
      "loss": 0.6483,
      "step": 166
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.058583491552465e-05,
      "loss": 0.6307,
      "step": 167
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9650304536132426e-05,
      "loss": 0.6614,
      "step": 168
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8734208617174988e-05,
      "loss": 0.6702,
      "step": 169
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.783776873795994e-05,
      "loss": 0.6492,
      "step": 170
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.696120172352025e-05,
      "loss": 0.6585,
      "step": 171
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6104719592169902e-05,
      "loss": 0.647,
      "step": 172
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.526852950422226e-05,
      "loss": 0.6616,
      "step": 173
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4452833711883628e-05,
      "loss": 0.6455,
      "step": 174
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3657829510333654e-05,
      "loss": 0.6177,
      "step": 175
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2883709190004955e-05,
      "loss": 0.6367,
      "step": 176
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2130659990073146e-05,
      "loss": 0.6641,
      "step": 177
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1398864053168534e-05,
      "loss": 0.6426,
      "step": 178
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0688498381320855e-05,
      "loss": 0.6559,
      "step": 179
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.999734793146998e-06,
      "loss": 0.6377,
      "step": 180
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.332739882292752e-06,
      "loss": 0.6667,
      "step": 181
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.687674977138116e-06,
      "loss": 0.6413,
      "step": 182
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.064696101776358e-06,
      "loss": 0.6565,
      "step": 183
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.463953938275858e-06,
      "loss": 0.6656,
      "step": 184
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.8855937902340576e-06,
      "loss": 0.6367,
      "step": 185
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.329755547632499e-06,
      "loss": 0.6492,
      "step": 186
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.7965736530010916e-06,
      "loss": 0.6551,
      "step": 187
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.286177068899989e-06,
      "loss": 0.6137,
      "step": 188
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.798689246727006e-06,
      "loss": 0.6535,
      "step": 189
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.3342280968580285e-06,
      "loss": 0.6491,
      "step": 190
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.892905960127546e-06,
      "loss": 0.6405,
      "step": 191
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.4748295806564356e-06,
      "loss": 0.6534,
      "step": 192
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.0801000800333877e-06,
      "loss": 0.618,
      "step": 193
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.708812932856253e-06,
      "loss": 0.642,
      "step": 194
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.3610579436393e-06,
      "loss": 0.6694,
      "step": 195
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.036919225091827e-06,
      "loss": 0.6383,
      "step": 196
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7364751777736332e-06,
      "loss": 0.6401,
      "step": 197
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.459798471131868e-06,
      "loss": 0.6092,
      "step": 198
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2069560259243328e-06,
      "loss": 0.6427,
      "step": 199
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.780089980330642e-07,
      "loss": 0.6305,
      "step": 200
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.730127636723539e-07,
      "loss": 0.6442,
      "step": 201
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.920169059947411e-07,
      "loss": 0.6332,
      "step": 202
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.3506520309813947e-07,
      "loss": 0.6433,
      "step": 203
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.0219561743707326e-07,
      "loss": 0.5965,
      "step": 204
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.9344028664056713e-07,
      "loss": 0.6531,
      "step": 205
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0882551573891953e-07,
      "loss": 0.6869,
      "step": 206
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.837177080119215e-08,
      "loss": 0.6386,
      "step": 207
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.209367398504746e-08,
      "loss": 0.6184,
      "step": 208
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.6399,
      "step": 209
    },
    {
      "epoch": 1.0,
      "step": 209,
      "total_flos": 10376851488768.0,
      "train_loss": 0.7131158461411033,
      "train_runtime": 3732.1205,
      "train_samples_per_second": 3.569,
      "train_steps_per_second": 0.056
    }
  ],
  "max_steps": 209,
  "num_train_epochs": 1,
  "total_flos": 10376851488768.0,
  "trial_name": null,
  "trial_params": null
}