{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 493,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 2.3484,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 2.5463,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.6055,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001995983935742972,
      "loss": 2.3676,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001991967871485944,
      "loss": 1.8278,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001991967871485944,
      "loss": 1.6644,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019879518072289158,
      "loss": 1.5494,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019839357429718877,
      "loss": 1.2689,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019799196787148596,
      "loss": 1.0911,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019759036144578314,
      "loss": 0.8925,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019718875502008033,
      "loss": 0.8251,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019678714859437752,
      "loss": 0.8871,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001963855421686747,
      "loss": 0.6684,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001959839357429719,
      "loss": 0.7377,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019558232931726906,
      "loss": 0.7108,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019518072289156628,
      "loss": 0.5971,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019477911646586347,
      "loss": 0.6384,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019437751004016066,
      "loss": 0.6022,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019397590361445782,
      "loss": 0.6303,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019357429718875504,
      "loss": 0.6137,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019317269076305223,
      "loss": 0.7437,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019277108433734942,
      "loss": 0.7448,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019236947791164658,
      "loss": 0.7302,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019196787148594377,
      "loss": 0.6401,
      "step": 24
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019156626506024098,
      "loss": 0.4414,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019116465863453817,
      "loss": 0.5489,
      "step": 26
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019076305220883533,
      "loss": 0.579,
      "step": 27
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019036144578313252,
      "loss": 0.575,
      "step": 28
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00018995983935742974,
      "loss": 0.7082,
      "step": 29
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00018955823293172693,
      "loss": 0.5186,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001891566265060241,
      "loss": 0.5562,
      "step": 31
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00018875502008032128,
      "loss": 0.644,
      "step": 32
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001883534136546185,
      "loss": 0.5768,
      "step": 33
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018795180722891569,
      "loss": 0.5801,
      "step": 34
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018755020080321285,
      "loss": 0.609,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018714859437751004,
      "loss": 0.5588,
      "step": 36
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018674698795180723,
      "loss": 0.6599,
      "step": 37
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018634538152610444,
      "loss": 0.6691,
      "step": 38
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001859437751004016,
      "loss": 0.5768,
      "step": 39
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001855421686746988,
      "loss": 0.5547,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018514056224899598,
      "loss": 0.5434,
      "step": 41
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001847389558232932,
      "loss": 0.5808,
      "step": 42
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018433734939759036,
      "loss": 0.6528,
      "step": 43
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018393574297188755,
      "loss": 0.6594,
      "step": 44
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018353413654618474,
      "loss": 0.5752,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018313253012048193,
      "loss": 0.7312,
      "step": 46
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00018273092369477912,
      "loss": 0.5985,
      "step": 47
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001823293172690763,
      "loss": 0.528,
      "step": 48
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001819277108433735,
      "loss": 0.5257,
      "step": 49
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001815261044176707,
      "loss": 0.5592,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001811244979919679,
      "loss": 0.5552,
      "step": 51
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00018072289156626507,
      "loss": 0.6648,
      "step": 52
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00018032128514056225,
      "loss": 0.7509,
      "step": 53
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00017991967871485944,
      "loss": 0.4606,
      "step": 54
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00017951807228915663,
      "loss": 0.5747,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00017911646586345382,
      "loss": 0.5779,
      "step": 56
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000178714859437751,
      "loss": 0.4876,
      "step": 57
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001783132530120482,
      "loss": 0.58,
      "step": 58
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001779116465863454,
      "loss": 0.5961,
      "step": 59
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00017751004016064258,
      "loss": 0.4444,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00017710843373493977,
      "loss": 0.6475,
      "step": 61
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017670682730923696,
      "loss": 0.5423,
      "step": 62
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017630522088353415,
      "loss": 0.5865,
      "step": 63
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017590361445783134,
      "loss": 0.5563,
      "step": 64
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017550200803212853,
      "loss": 0.4826,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017510040160642571,
      "loss": 0.5253,
      "step": 66
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001746987951807229,
      "loss": 0.6209,
      "step": 67
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001742971887550201,
      "loss": 0.4979,
      "step": 68
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017389558232931728,
      "loss": 0.6658,
      "step": 69
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017349397590361447,
      "loss": 0.4918,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017309236947791166,
      "loss": 0.6668,
      "step": 71
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00017269076305220885,
      "loss": 0.5992,
      "step": 72
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00017228915662650604,
      "loss": 0.6433,
      "step": 73
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00017188755020080323,
      "loss": 0.647,
      "step": 74
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00017148594377510042,
      "loss": 0.5385,
      "step": 75
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001710843373493976,
      "loss": 0.5451,
      "step": 76
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00017068273092369477,
      "loss": 0.4437,
      "step": 77
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00017028112449799199,
      "loss": 0.4511,
      "step": 78
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00016987951807228917,
      "loss": 0.5662,
      "step": 79
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00016947791164658636,
      "loss": 0.6221,
      "step": 80
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00016907630522088353,
      "loss": 0.567,
      "step": 81
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016867469879518074,
      "loss": 0.5783,
      "step": 82
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016827309236947793,
      "loss": 0.5302,
      "step": 83
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016787148594377512,
      "loss": 0.6094,
      "step": 84
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016746987951807228,
      "loss": 0.588,
      "step": 85
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016706827309236947,
      "loss": 0.5507,
      "step": 86
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.4017,
      "step": 87
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016626506024096388,
      "loss": 0.5631,
      "step": 88
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016586345381526104,
      "loss": 0.5022,
      "step": 89
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016546184738955823,
      "loss": 0.4663,
      "step": 90
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016506024096385545,
      "loss": 0.4863,
      "step": 91
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016465863453815263,
      "loss": 0.5595,
      "step": 92
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001642570281124498,
      "loss": 0.5928,
      "step": 93
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016385542168674699,
      "loss": 0.5443,
      "step": 94
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016345381526104417,
      "loss": 0.6472,
      "step": 95
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001630522088353414,
      "loss": 0.5789,
      "step": 96
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00016265060240963855,
      "loss": 0.4732,
      "step": 97
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00016224899598393574,
      "loss": 0.4843,
      "step": 98
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00016184738955823293,
      "loss": 0.6245,
      "step": 99
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00016144578313253015,
      "loss": 0.6005,
      "step": 100
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001610441767068273,
      "loss": 0.7296,
      "step": 101
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001606425702811245,
      "loss": 0.5073,
      "step": 102
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001602409638554217,
      "loss": 0.4158,
      "step": 103
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00015983935742971888,
      "loss": 0.6197,
      "step": 104
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00015943775100401607,
      "loss": 0.6124,
      "step": 105
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015903614457831326,
      "loss": 0.3915,
      "step": 106
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015863453815261045,
      "loss": 0.5916,
      "step": 107
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015823293172690763,
      "loss": 0.4174,
      "step": 108
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015783132530120482,
      "loss": 0.4335,
      "step": 109
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000157429718875502,
      "loss": 0.5405,
      "step": 110
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001570281124497992,
      "loss": 0.5486,
      "step": 111
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001566265060240964,
      "loss": 0.5357,
      "step": 112
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015622489959839358,
      "loss": 0.4446,
      "step": 113
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015582329317269077,
      "loss": 0.4985,
      "step": 114
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015542168674698796,
      "loss": 0.5429,
      "step": 115
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015502008032128515,
      "loss": 0.5076,
      "step": 116
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015461847389558234,
      "loss": 0.5397,
      "step": 117
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015421686746987953,
      "loss": 0.5309,
      "step": 118
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015381526104417672,
      "loss": 0.5043,
      "step": 119
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001534136546184739,
      "loss": 0.5628,
      "step": 120
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001530120481927711,
      "loss": 0.5627,
      "step": 121
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00015261044176706828,
      "loss": 0.4973,
      "step": 122
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00015220883534136547,
      "loss": 0.6026,
      "step": 123
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00015180722891566266,
      "loss": 0.5615,
      "step": 124
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00015140562248995985,
      "loss": 0.5713,
      "step": 125
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00015100401606425701,
      "loss": 0.4732,
      "step": 126
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00015060240963855423,
      "loss": 0.6171,
      "step": 127
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00015020080321285142,
      "loss": 0.4272,
      "step": 128
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001497991967871486,
      "loss": 0.5087,
      "step": 129
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00014939759036144577,
      "loss": 0.4022,
      "step": 130
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000148995983935743,
      "loss": 0.6336,
      "step": 131
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014859437751004018,
      "loss": 0.4404,
      "step": 132
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014819277108433737,
      "loss": 0.5488,
      "step": 133
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014779116465863453,
      "loss": 0.5313,
      "step": 134
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014738955823293172,
      "loss": 0.4526,
      "step": 135
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014698795180722893,
      "loss": 0.434,
      "step": 136
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014658634538152612,
      "loss": 0.5141,
      "step": 137
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014618473895582328,
      "loss": 0.4783,
      "step": 138
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014578313253012047,
      "loss": 0.5319,
      "step": 139
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001453815261044177,
      "loss": 0.509,
      "step": 140
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014497991967871488,
      "loss": 0.6049,
      "step": 141
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014457831325301204,
      "loss": 0.6876,
      "step": 142
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014417670682730923,
      "loss": 0.5849,
      "step": 143
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014377510040160642,
      "loss": 0.5415,
      "step": 144
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014337349397590364,
      "loss": 0.5939,
      "step": 145
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001429718875502008,
      "loss": 0.4664,
      "step": 146
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000142570281124498,
      "loss": 0.527,
      "step": 147
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00014216867469879518,
      "loss": 0.4095,
      "step": 148
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001417670682730924,
      "loss": 0.5033,
      "step": 149
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00014136546184738956,
      "loss": 0.6287,
      "step": 150
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00014096385542168674,
      "loss": 0.5513,
      "step": 151
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00014056224899598393,
      "loss": 0.4836,
      "step": 152
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00014016064257028115,
      "loss": 0.4919,
      "step": 153
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00013975903614457834,
      "loss": 0.4779,
      "step": 154
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001393574297188755,
      "loss": 0.5458,
      "step": 155
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001389558232931727,
      "loss": 0.5449,
      "step": 156
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00013855421686746988,
      "loss": 0.5182,
      "step": 157
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001381526104417671,
      "loss": 0.6282,
      "step": 158
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00013775100401606426,
      "loss": 0.365,
      "step": 159
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00013734939759036145,
      "loss": 0.5731,
      "step": 160
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00013694779116465864,
      "loss": 0.4345,
      "step": 161
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00013654618473895585,
      "loss": 0.5463,
      "step": 162
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00013614457831325302,
      "loss": 0.4878,
      "step": 163
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001357429718875502,
      "loss": 0.5038,
      "step": 164
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001353413654618474,
      "loss": 0.4764,
      "step": 165
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013493975903614458,
      "loss": 0.5113,
      "step": 166
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013453815261044177,
      "loss": 0.4931,
      "step": 167
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013413654618473896,
      "loss": 0.5509,
      "step": 168
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013373493975903615,
      "loss": 0.5908,
      "step": 169
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.4747,
      "step": 170
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00013293172690763053,
      "loss": 0.4458,
      "step": 171
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00013253012048192772,
      "loss": 0.449,
      "step": 172
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001321285140562249,
      "loss": 0.4831,
      "step": 173
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001317269076305221,
      "loss": 0.3903,
      "step": 174
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00013132530120481929,
      "loss": 0.363,
      "step": 175
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00013092369477911648,
      "loss": 0.5235,
      "step": 176
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00013052208835341366,
      "loss": 0.4631,
      "step": 177
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00013012048192771085,
      "loss": 0.5049,
      "step": 178
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00012971887550200804,
      "loss": 0.531,
      "step": 179
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012931726907630523,
      "loss": 0.4807,
      "step": 180
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012891566265060242,
      "loss": 0.5766,
      "step": 181
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001285140562248996,
      "loss": 0.5113,
      "step": 182
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001281124497991968,
      "loss": 0.5385,
      "step": 183
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012771084337349396,
      "loss": 0.4967,
      "step": 184
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012730923694779118,
      "loss": 0.4895,
      "step": 185
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012690763052208837,
      "loss": 0.3827,
      "step": 186
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012650602409638556,
      "loss": 0.4897,
      "step": 187
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012610441767068272,
      "loss": 0.5642,
      "step": 188
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012570281124497994,
      "loss": 0.4989,
      "step": 189
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00012530120481927712,
      "loss": 0.5212,
      "step": 190
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001248995983935743,
      "loss": 0.6401,
      "step": 191
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00012449799196787148,
      "loss": 0.4974,
      "step": 192
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001240963855421687,
      "loss": 0.4409,
      "step": 193
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00012369477911646588,
      "loss": 0.5508,
      "step": 194
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00012329317269076307,
      "loss": 0.738,
      "step": 195
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00012289156626506023,
      "loss": 0.4174,
      "step": 196
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00012248995983935742,
      "loss": 0.4254,
      "step": 197
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00012208835341365464,
      "loss": 0.6255,
      "step": 198
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00012168674698795181,
      "loss": 0.5013,
      "step": 199
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000121285140562249,
      "loss": 0.4475,
      "step": 200
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00012088353413654618,
      "loss": 0.463,
      "step": 201
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001204819277108434,
      "loss": 0.475,
      "step": 202
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00012008032128514057,
      "loss": 0.4786,
      "step": 203
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00011967871485943776,
      "loss": 0.5241,
      "step": 204
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011927710843373494,
      "loss": 0.529,
      "step": 205
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011887550200803212,
      "loss": 0.5723,
      "step": 206
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011847389558232933,
      "loss": 0.4576,
      "step": 207
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011807228915662652,
      "loss": 0.542,
      "step": 208
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011767068273092369,
      "loss": 0.4835,
      "step": 209
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011726907630522088,
      "loss": 0.581,
      "step": 210
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011686746987951808,
      "loss": 0.5406,
      "step": 211
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011646586345381527,
      "loss": 0.4382,
      "step": 212
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011606425702811245,
      "loss": 0.5514,
      "step": 213
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011566265060240964,
      "loss": 0.5362,
      "step": 214
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00011526104417670683,
      "loss": 0.53,
      "step": 215
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00011485943775100403,
      "loss": 0.6346,
      "step": 216
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001144578313253012,
      "loss": 0.517,
      "step": 217
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001140562248995984,
      "loss": 0.6743,
      "step": 218
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00011365461847389558,
      "loss": 0.5228,
      "step": 219
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011325301204819279,
      "loss": 0.4498,
      "step": 220
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011285140562248996,
      "loss": 0.3413,
      "step": 221
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011244979919678715,
      "loss": 0.5713,
      "step": 222
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011204819277108434,
      "loss": 0.3474,
      "step": 223
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011164658634538152,
      "loss": 0.4452,
      "step": 224
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011124497991967872,
      "loss": 0.5386,
      "step": 225
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011084337349397591,
      "loss": 0.5245,
      "step": 226
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001104417670682731,
      "loss": 0.5415,
      "step": 227
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011004016064257027,
      "loss": 0.6118,
      "step": 228
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00010963855421686749,
      "loss": 0.5373,
      "step": 229
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010923694779116467,
      "loss": 0.524,
      "step": 230
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010883534136546186,
      "loss": 0.402,
      "step": 231
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010843373493975903,
      "loss": 0.4581,
      "step": 232
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010803212851405625,
      "loss": 0.585,
      "step": 233
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010763052208835342,
      "loss": 0.4727,
      "step": 234
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010722891566265061,
      "loss": 0.5338,
      "step": 235
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010682730923694779,
      "loss": 0.4985,
      "step": 236
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010642570281124498,
      "loss": 0.4611,
      "step": 237
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010602409638554218,
      "loss": 0.5,
      "step": 238
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010562248995983937,
      "loss": 0.4257,
      "step": 239
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010522088353413654,
      "loss": 0.5235,
      "step": 240
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010481927710843373,
      "loss": 0.4891,
      "step": 241
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010441767068273094,
      "loss": 0.589,
      "step": 242
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010401606425702813,
      "loss": 0.6157,
      "step": 243
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001036144578313253,
      "loss": 0.4803,
      "step": 244
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010321285140562249,
      "loss": 0.5102,
      "step": 245
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010281124497991968,
      "loss": 0.5567,
      "step": 246
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010240963855421688,
      "loss": 0.4538,
      "step": 247
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010200803212851406,
      "loss": 0.4877,
      "step": 248
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010160642570281125,
      "loss": 0.5516,
      "step": 249
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010120481927710844,
      "loss": 0.4773,
      "step": 250
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010080321285140564,
      "loss": 0.476,
      "step": 251
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010040160642570282,
      "loss": 0.5584,
      "step": 252
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 0.4742,
      "step": 253
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.95983935742972e-05,
      "loss": 0.4615,
      "step": 254
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.919678714859438e-05,
      "loss": 0.4471,
      "step": 255
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.879518072289157e-05,
      "loss": 0.4661,
      "step": 256
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.839357429718876e-05,
      "loss": 0.3569,
      "step": 257
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.799196787148595e-05,
      "loss": 0.4938,
      "step": 258
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.759036144578314e-05,
      "loss": 0.5879,
      "step": 259
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.718875502008033e-05,
      "loss": 0.493,
      "step": 260
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.678714859437752e-05,
      "loss": 0.385,
      "step": 261
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.638554216867471e-05,
      "loss": 0.485,
      "step": 262
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.598393574297188e-05,
      "loss": 0.4833,
      "step": 263
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.558232931726909e-05,
      "loss": 0.5572,
      "step": 264
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.518072289156626e-05,
      "loss": 0.5039,
      "step": 265
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.477911646586346e-05,
      "loss": 0.5308,
      "step": 266
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.437751004016064e-05,
      "loss": 0.3708,
      "step": 267
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.397590361445784e-05,
      "loss": 0.4779,
      "step": 268
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.357429718875502e-05,
      "loss": 0.4807,
      "step": 269
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.317269076305222e-05,
      "loss": 0.5036,
      "step": 270
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.27710843373494e-05,
      "loss": 0.5056,
      "step": 271
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.23694779116466e-05,
      "loss": 0.5143,
      "step": 272
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.196787148594378e-05,
      "loss": 0.5403,
      "step": 273
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.156626506024096e-05,
      "loss": 0.4212,
      "step": 274
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.116465863453815e-05,
      "loss": 0.4461,
      "step": 275
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.076305220883534e-05,
      "loss": 0.4122,
      "step": 276
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.036144578313253e-05,
      "loss": 0.4249,
      "step": 277
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.995983935742972e-05,
      "loss": 0.4376,
      "step": 278
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.955823293172691e-05,
      "loss": 0.5155,
      "step": 279
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.91566265060241e-05,
      "loss": 0.4269,
      "step": 280
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.875502008032129e-05,
      "loss": 0.5717,
      "step": 281
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.835341365461848e-05,
      "loss": 0.5976,
      "step": 282
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.795180722891567e-05,
      "loss": 0.3902,
      "step": 283
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.755020080321286e-05,
      "loss": 0.543,
      "step": 284
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.714859437751005e-05,
      "loss": 0.4176,
      "step": 285
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.674698795180724e-05,
      "loss": 0.5327,
      "step": 286
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.634538152610442e-05,
      "loss": 0.4426,
      "step": 287
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.594377510040161e-05,
      "loss": 0.5193,
      "step": 288
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.55421686746988e-05,
      "loss": 0.4712,
      "step": 289
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.514056224899599e-05,
      "loss": 0.4665,
      "step": 290
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.473895582329318e-05,
      "loss": 0.3824,
      "step": 291
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.433734939759037e-05,
      "loss": 0.5133,
      "step": 292
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.393574297188756e-05,
      "loss": 0.516,
      "step": 293
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.353413654618474e-05,
      "loss": 0.4913,
      "step": 294
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.313253012048194e-05,
      "loss": 0.486,
      "step": 295
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.273092369477911e-05,
      "loss": 0.4943,
      "step": 296
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.232931726907632e-05,
      "loss": 0.5291,
      "step": 297
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.192771084337349e-05,
      "loss": 0.4005,
      "step": 298
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.15261044176707e-05,
      "loss": 0.4921,
      "step": 299
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.112449799196787e-05,
      "loss": 0.5235,
      "step": 300
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.072289156626507e-05,
      "loss": 0.5263,
      "step": 301
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.032128514056225e-05,
      "loss": 0.3585,
      "step": 302
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.991967871485944e-05,
      "loss": 0.4826,
      "step": 303
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.951807228915663e-05,
      "loss": 0.4486,
      "step": 304
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.911646586345382e-05,
      "loss": 0.4879,
      "step": 305
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.8714859437751e-05,
      "loss": 0.5017,
      "step": 306
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.83132530120482e-05,
      "loss": 0.5536,
      "step": 307
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.791164658634539e-05,
      "loss": 0.5105,
      "step": 308
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.751004016064257e-05,
      "loss": 0.4379,
      "step": 309
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.710843373493976e-05,
      "loss": 0.5182,
      "step": 310
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.670682730923695e-05,
      "loss": 0.5573,
      "step": 311
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.630522088353414e-05,
      "loss": 0.5426,
      "step": 312
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.590361445783133e-05,
      "loss": 0.4325,
      "step": 313
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.550200803212851e-05,
      "loss": 0.4559,
      "step": 314
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.510040160642571e-05,
      "loss": 0.3663,
      "step": 315
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.469879518072289e-05,
      "loss": 0.4276,
      "step": 316
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.429718875502009e-05,
      "loss": 0.4663,
      "step": 317
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.389558232931726e-05,
      "loss": 0.5068,
      "step": 318
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.349397590361447e-05,
      "loss": 0.5,
      "step": 319
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.309236947791164e-05,
      "loss": 0.431,
      "step": 320
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.269076305220885e-05,
      "loss": 0.4133,
      "step": 321
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.228915662650602e-05,
      "loss": 0.3705,
      "step": 322
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.188755020080321e-05,
      "loss": 0.419,
      "step": 323
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.14859437751004e-05,
      "loss": 0.5409,
      "step": 324
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.108433734939759e-05,
      "loss": 0.5186,
      "step": 325
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.068273092369478e-05,
      "loss": 0.438,
      "step": 326
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.028112449799197e-05,
      "loss": 0.4709,
      "step": 327
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.987951807228917e-05,
      "loss": 0.3494,
      "step": 328
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.947791164658635e-05,
      "loss": 0.4782,
      "step": 329
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.907630522088355e-05,
      "loss": 0.4365,
      "step": 330
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.867469879518072e-05,
      "loss": 0.4108,
      "step": 331
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.827309236947793e-05,
      "loss": 0.429,
      "step": 332
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.78714859437751e-05,
      "loss": 0.3968,
      "step": 333
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.746987951807229e-05,
      "loss": 0.5652,
      "step": 334
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.706827309236948e-05,
      "loss": 0.435,
      "step": 335
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.3639,
      "step": 336
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.626506024096386e-05,
      "loss": 0.4134,
      "step": 337
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.586345381526105e-05,
      "loss": 0.5979,
      "step": 338
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.546184738955824e-05,
      "loss": 0.4856,
      "step": 339
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.506024096385543e-05,
      "loss": 0.4834,
      "step": 340
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.465863453815262e-05,
      "loss": 0.5589,
      "step": 341
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.42570281124498e-05,
      "loss": 0.4846,
      "step": 342
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.385542168674698e-05,
      "loss": 0.3595,
      "step": 343
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.345381526104418e-05,
      "loss": 0.4102,
      "step": 344
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.305220883534136e-05,
      "loss": 0.3999,
      "step": 345
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.265060240963856e-05,
      "loss": 0.3772,
      "step": 346
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.224899598393574e-05,
      "loss": 0.4575,
      "step": 347
    },
    {
      "epoch": 0.71,
      "learning_rate": 6.184738955823294e-05,
      "loss": 0.4095,
      "step": 348
    },
    {
      "epoch": 0.71,
      "learning_rate": 6.144578313253012e-05,
      "loss": 0.4449,
      "step": 349
    },
    {
      "epoch": 0.71,
      "learning_rate": 6.104417670682732e-05,
      "loss": 0.5009,
      "step": 350
    },
    {
      "epoch": 0.71,
      "learning_rate": 6.06425702811245e-05,
      "loss": 0.3336,
      "step": 351
    },
    {
      "epoch": 0.71,
      "learning_rate": 6.02409638554217e-05,
      "loss": 0.4671,
      "step": 352
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.983935742971888e-05,
      "loss": 0.4137,
      "step": 353
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.943775100401606e-05,
      "loss": 0.5014,
      "step": 354
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.903614457831326e-05,
      "loss": 0.557,
      "step": 355
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.863453815261044e-05,
      "loss": 0.5651,
      "step": 356
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.823293172690764e-05,
      "loss": 0.5723,
      "step": 357
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.783132530120482e-05,
      "loss": 0.559,
      "step": 358
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.7429718875502015e-05,
      "loss": 0.4025,
      "step": 359
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.70281124497992e-05,
      "loss": 0.4925,
      "step": 360
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.6626506024096394e-05,
      "loss": 0.377,
      "step": 361
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.6224899598393576e-05,
      "loss": 0.2866,
      "step": 362
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.582329317269076e-05,
      "loss": 0.5416,
      "step": 363
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.5421686746987955e-05,
      "loss": 0.487,
      "step": 364
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.502008032128514e-05,
      "loss": 0.417,
      "step": 365
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.461847389558233e-05,
      "loss": 0.4206,
      "step": 366
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.4216867469879516e-05,
      "loss": 0.4299,
      "step": 367
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.381526104417671e-05,
      "loss": 0.5043,
      "step": 368
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.3413654618473894e-05,
      "loss": 0.3499,
      "step": 369
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.301204819277109e-05,
      "loss": 0.3456,
      "step": 370
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.261044176706827e-05,
      "loss": 0.3828,
      "step": 371
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.220883534136547e-05,
      "loss": 0.4296,
      "step": 372
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.180722891566265e-05,
      "loss": 0.3614,
      "step": 373
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.140562248995984e-05,
      "loss": 0.5085,
      "step": 374
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.100401606425703e-05,
      "loss": 0.4497,
      "step": 375
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.060240963855422e-05,
      "loss": 0.4421,
      "step": 376
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.020080321285141e-05,
      "loss": 0.411,
      "step": 377
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.97991967871486e-05,
      "loss": 0.4727,
      "step": 378
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.9397590361445786e-05,
      "loss": 0.4739,
      "step": 379
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.8995983935742975e-05,
      "loss": 0.5005,
      "step": 380
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.8594377510040165e-05,
      "loss": 0.4776,
      "step": 381
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.8192771084337354e-05,
      "loss": 0.4337,
      "step": 382
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.779116465863454e-05,
      "loss": 0.3575,
      "step": 383
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.738955823293173e-05,
      "loss": 0.5325,
      "step": 384
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.698795180722892e-05,
      "loss": 0.4765,
      "step": 385
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.658634538152611e-05,
      "loss": 0.4794,
      "step": 386
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.61847389558233e-05,
      "loss": 0.5106,
      "step": 387
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.578313253012048e-05,
      "loss": 0.3883,
      "step": 388
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.538152610441767e-05,
      "loss": 0.4342,
      "step": 389
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.497991967871486e-05,
      "loss": 0.4893,
      "step": 390
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.457831325301205e-05,
      "loss": 0.4752,
      "step": 391
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.417670682730924e-05,
      "loss": 0.4855,
      "step": 392
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.377510040160643e-05,
      "loss": 0.4693,
      "step": 393
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.337349397590362e-05,
      "loss": 0.3851,
      "step": 394
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.297188755020081e-05,
      "loss": 0.5259,
      "step": 395
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.2570281124497996e-05,
      "loss": 0.476,
      "step": 396
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.2168674698795186e-05,
      "loss": 0.4004,
      "step": 397
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.176706827309237e-05,
      "loss": 0.4326,
      "step": 398
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.136546184738956e-05,
      "loss": 0.423,
      "step": 399
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.0963855421686746e-05,
      "loss": 0.4768,
      "step": 400
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.0562248995983936e-05,
      "loss": 0.5186,
      "step": 401
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.0160642570281125e-05,
      "loss": 0.495,
      "step": 402
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.9759036144578314e-05,
      "loss": 0.3834,
      "step": 403
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.93574297188755e-05,
      "loss": 0.3187,
      "step": 404
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.895582329317269e-05,
      "loss": 0.4442,
      "step": 405
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.855421686746988e-05,
      "loss": 0.4514,
      "step": 406
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.815261044176707e-05,
      "loss": 0.4302,
      "step": 407
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.7751004016064253e-05,
      "loss": 0.4411,
      "step": 408
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.734939759036144e-05,
      "loss": 0.5643,
      "step": 409
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.694779116465863e-05,
      "loss": 0.4168,
      "step": 410
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.654618473895582e-05,
      "loss": 0.5073,
      "step": 411
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.614457831325301e-05,
      "loss": 0.5055,
      "step": 412
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.57429718875502e-05,
      "loss": 0.451,
      "step": 413
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.534136546184739e-05,
      "loss": 0.529,
      "step": 414
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.4939759036144585e-05,
      "loss": 0.4821,
      "step": 415
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.4538152610441774e-05,
      "loss": 0.4862,
      "step": 416
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.413654618473896e-05,
      "loss": 0.4247,
      "step": 417
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.3734939759036146e-05,
      "loss": 0.4721,
      "step": 418
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4703,
      "step": 419
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.2931726907630524e-05,
      "loss": 0.3788,
      "step": 420
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.253012048192771e-05,
      "loss": 0.4845,
      "step": 421
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.21285140562249e-05,
      "loss": 0.3343,
      "step": 422
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.172690763052209e-05,
      "loss": 0.498,
      "step": 423
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.132530120481928e-05,
      "loss": 0.5233,
      "step": 424
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.092369477911647e-05,
      "loss": 0.4114,
      "step": 425
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.052208835341366e-05,
      "loss": 0.5315,
      "step": 426
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.012048192771085e-05,
      "loss": 0.4946,
      "step": 427
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.971887550200803e-05,
      "loss": 0.4793,
      "step": 428
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.931726907630522e-05,
      "loss": 0.4833,
      "step": 429
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.891566265060241e-05,
      "loss": 0.5622,
      "step": 430
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.85140562248996e-05,
      "loss": 0.609,
      "step": 431
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.8112449799196788e-05,
      "loss": 0.4482,
      "step": 432
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.7710843373493977e-05,
      "loss": 0.4253,
      "step": 433
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.7309236947791167e-05,
      "loss": 0.3964,
      "step": 434
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.6907630522088356e-05,
      "loss": 0.4911,
      "step": 435
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.6506024096385545e-05,
      "loss": 0.5473,
      "step": 436
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.6104417670682734e-05,
      "loss": 0.4132,
      "step": 437
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.570281124497992e-05,
      "loss": 0.4096,
      "step": 438
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.530120481927711e-05,
      "loss": 0.3632,
      "step": 439
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.48995983935743e-05,
      "loss": 0.4207,
      "step": 440
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.4497991967871488e-05,
      "loss": 0.4925,
      "step": 441
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.4096385542168677e-05,
      "loss": 0.3735,
      "step": 442
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.3694779116465866e-05,
      "loss": 0.5045,
      "step": 443
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.3293172690763055e-05,
      "loss": 0.4654,
      "step": 444
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.289156626506024e-05,
      "loss": 0.4929,
      "step": 445
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.248995983935743e-05,
      "loss": 0.4846,
      "step": 446
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.208835341365462e-05,
      "loss": 0.4246,
      "step": 447
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.168674698795181e-05,
      "loss": 0.5278,
      "step": 448
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.1285140562248998e-05,
      "loss": 0.4004,
      "step": 449
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.0883534136546184e-05,
      "loss": 0.4441,
      "step": 450
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.0481927710843373e-05,
      "loss": 0.4555,
      "step": 451
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.0080321285140562e-05,
      "loss": 0.3512,
      "step": 452
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.967871485943775e-05,
      "loss": 0.4559,
      "step": 453
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.927710843373494e-05,
      "loss": 0.4225,
      "step": 454
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.8875502008032127e-05,
      "loss": 0.483,
      "step": 455
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.8473895582329316e-05,
      "loss": 0.4765,
      "step": 456
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.8072289156626505e-05,
      "loss": 0.604,
      "step": 457
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.7670682730923694e-05,
      "loss": 0.4636,
      "step": 458
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.7269076305220887e-05,
      "loss": 0.4905,
      "step": 459
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.6867469879518073e-05,
      "loss": 0.4039,
      "step": 460
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6465863453815262e-05,
      "loss": 0.3915,
      "step": 461
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.606425702811245e-05,
      "loss": 0.3922,
      "step": 462
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.566265060240964e-05,
      "loss": 0.579,
      "step": 463
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.526104417670683e-05,
      "loss": 0.3441,
      "step": 464
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.4859437751004016e-05,
      "loss": 0.4649,
      "step": 465
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4457831325301205e-05,
      "loss": 0.4807,
      "step": 466
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4056224899598394e-05,
      "loss": 0.4659,
      "step": 467
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3654618473895583e-05,
      "loss": 0.2945,
      "step": 468
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3253012048192772e-05,
      "loss": 0.4214,
      "step": 469
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.285140562248996e-05,
      "loss": 0.4886,
      "step": 470
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.244979919678715e-05,
      "loss": 0.5413,
      "step": 471
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.2048192771084338e-05,
      "loss": 0.4392,
      "step": 472
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.1646586345381528e-05,
      "loss": 0.5799,
      "step": 473
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.1244979919678715e-05,
      "loss": 0.4651,
      "step": 474
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0843373493975904e-05,
      "loss": 0.4336,
      "step": 475
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.0441767068273092e-05,
      "loss": 0.6531,
      "step": 476
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.0040160642570281e-05,
      "loss": 0.4463,
      "step": 477
    },
    {
      "epoch": 0.97,
      "learning_rate": 9.63855421686747e-06,
      "loss": 0.3375,
      "step": 478
    },
    {
      "epoch": 0.97,
      "learning_rate": 9.236947791164658e-06,
      "loss": 0.3812,
      "step": 479
    },
    {
      "epoch": 0.97,
      "learning_rate": 8.835341365461847e-06,
      "loss": 0.3803,
      "step": 480
    },
    {
      "epoch": 0.98,
      "learning_rate": 8.433734939759036e-06,
      "loss": 0.5742,
      "step": 481
    },
    {
      "epoch": 0.98,
      "learning_rate": 8.032128514056226e-06,
      "loss": 0.4986,
      "step": 482
    },
    {
      "epoch": 0.98,
      "learning_rate": 7.630522088353415e-06,
      "loss": 0.3414,
      "step": 483
    },
    {
      "epoch": 0.98,
      "learning_rate": 7.228915662650602e-06,
      "loss": 0.3588,
      "step": 484
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.827309236947792e-06,
      "loss": 0.4386,
      "step": 485
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.42570281124498e-06,
      "loss": 0.35,
      "step": 486
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.024096385542169e-06,
      "loss": 0.3784,
      "step": 487
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.622489959839358e-06,
      "loss": 0.4395,
      "step": 488
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.220883534136546e-06,
      "loss": 0.4529,
      "step": 489
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.819277108433735e-06,
      "loss": 0.3706,
      "step": 490
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.417670682730924e-06,
      "loss": 0.4192,
      "step": 491
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.016064257028113e-06,
      "loss": 0.4437,
      "step": 492
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.614457831325301e-06,
      "loss": 0.4391,
      "step": 493
    }
  ],
  "logging_steps": 1,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 418467312304128.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}