{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.629735935706085,
  "eval_steps": 500,
  "global_step": 1378,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.00019999989520267283,
      "loss": 1.377,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019999958081091102,
      "loss": 1.2613,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019999905682537348,
      "loss": 1.1324,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999832324715846,
      "loss": 1.0451,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999738007780348,
      "loss": 1.0011,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001999962273192854,
      "loss": 0.9464,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999486497402038,
      "loss": 0.9247,
      "step": 7
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019999329304486377,
      "loss": 0.8769,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019999151153511023,
      "loss": 0.8683,
      "step": 9
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019998952044849376,
      "loss": 0.8325,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019998731978918756,
      "loss": 0.7987,
      "step": 11
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019998490956180405,
      "loss": 0.7877,
      "step": 12
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000199982289771395,
      "loss": 0.7496,
      "step": 13
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019997946042345127,
      "loss": 0.7487,
      "step": 14
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019997642152390314,
      "loss": 0.7427,
      "step": 15
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001999731730791199,
      "loss": 0.718,
      "step": 16
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019996971509591012,
      "loss": 0.7124,
      "step": 17
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019996604758152158,
      "loss": 0.7083,
      "step": 18
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019996217054364115,
      "loss": 0.6978,
      "step": 19
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019995808399039496,
      "loss": 0.6929,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019995378793034814,
      "loss": 0.6645,
      "step": 21
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000199949282372505,
      "loss": 0.6619,
      "step": 22
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019994456732630903,
      "loss": 0.666,
      "step": 23
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019993964280164264,
      "loss": 0.6554,
      "step": 24
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019993450880882735,
      "loss": 0.6517,
      "step": 25
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019992916535862385,
      "loss": 0.6453,
      "step": 26
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019992361246223158,
      "loss": 0.644,
      "step": 27
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019991785013128923,
      "loss": 0.6352,
      "step": 28
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001999118783778743,
      "loss": 0.6269,
      "step": 29
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019990569721450326,
      "loss": 0.6274,
      "step": 30
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019989930665413147,
      "loss": 0.6236,
      "step": 31
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019989270671015325,
      "loss": 0.6175,
      "step": 32
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019988589739640172,
      "loss": 0.6203,
      "step": 33
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019987887872714878,
      "loss": 0.6084,
      "step": 34
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019987165071710527,
      "loss": 0.6063,
      "step": 35
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001998642133814207,
      "loss": 0.6059,
      "step": 36
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019985656673568328,
      "loss": 0.6011,
      "step": 37
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019984871079591998,
      "loss": 0.6,
      "step": 38
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019984064557859648,
      "loss": 0.6012,
      "step": 39
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019983237110061697,
      "loss": 0.5957,
      "step": 40
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001998238873793244,
      "loss": 0.6014,
      "step": 41
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001998151944325001,
      "loss": 0.5976,
      "step": 42
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001998062922783641,
      "loss": 0.5934,
      "step": 43
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001997971809355748,
      "loss": 0.5947,
      "step": 44
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001997878604232291,
      "loss": 0.5852,
      "step": 45
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019977833076086229,
      "loss": 0.5919,
      "step": 46
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019976859196844804,
      "loss": 0.5752,
      "step": 47
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019975864406639833,
      "loss": 0.5744,
      "step": 48
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019974848707556345,
      "loss": 0.5782,
      "step": 49
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019973812101723188,
      "loss": 0.5759,
      "step": 50
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019972754591313034,
      "loss": 0.5714,
      "step": 51
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019971676178542368,
      "loss": 0.5622,
      "step": 52
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019970576865671488,
      "loss": 0.5687,
      "step": 53
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001996945665500449,
      "loss": 0.5712,
      "step": 54
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001996831554888928,
      "loss": 0.5655,
      "step": 55
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019967153549717553,
      "loss": 0.5612,
      "step": 56
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000199659706599248,
      "loss": 0.5619,
      "step": 57
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001996476688199029,
      "loss": 0.5624,
      "step": 58
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001996354221843708,
      "loss": 0.5701,
      "step": 59
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019962296671832003,
      "loss": 0.5636,
      "step": 60
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001996103024478565,
      "loss": 0.5652,
      "step": 61
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019959742939952392,
      "loss": 0.5652,
      "step": 62
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019958434760030346,
      "loss": 0.5581,
      "step": 63
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001995710570776139,
      "loss": 0.5585,
      "step": 64
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019955755785931145,
      "loss": 0.5539,
      "step": 65
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019954384997368976,
      "loss": 0.5562,
      "step": 66
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019952993344947984,
      "loss": 0.5521,
      "step": 67
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019951580831584993,
      "loss": 0.5522,
      "step": 68
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001995014746024056,
      "loss": 0.5546,
      "step": 69
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019948693233918952,
      "loss": 0.5513,
      "step": 70
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019947218155668152,
      "loss": 0.5574,
      "step": 71
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019945722228579846,
      "loss": 0.5457,
      "step": 72
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019944205455789415,
      "loss": 0.5487,
      "step": 73
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019942667840475931,
      "loss": 0.5464,
      "step": 74
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001994110938586216,
      "loss": 0.5435,
      "step": 75
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019939530095214536,
      "loss": 0.5516,
      "step": 76
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019937929971843165,
      "loss": 0.5482,
      "step": 77
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019936309019101826,
      "loss": 0.542,
      "step": 78
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019934667240387944,
      "loss": 0.5375,
      "step": 79
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019933004639142605,
      "loss": 0.5394,
      "step": 80
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001993132121885053,
      "loss": 0.5413,
      "step": 81
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019929616983040073,
      "loss": 0.5382,
      "step": 82
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019927891935283225,
      "loss": 0.5352,
      "step": 83
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019926146079195594,
      "loss": 0.5415,
      "step": 84
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019924379418436404,
      "loss": 0.5315,
      "step": 85
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019922591956708478,
      "loss": 0.5352,
      "step": 86
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001992078369775824,
      "loss": 0.5491,
      "step": 87
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019918954645375706,
      "loss": 0.5348,
      "step": 88
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019917104803394468,
      "loss": 0.534,
      "step": 89
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000199152341756917,
      "loss": 0.5417,
      "step": 90
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019913342766188138,
      "loss": 0.5326,
      "step": 91
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019911430578848074,
      "loss": 0.5308,
      "step": 92
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019909497617679348,
      "loss": 0.5311,
      "step": 93
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019907543886733348,
      "loss": 0.5348,
      "step": 94
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019905569390104986,
      "loss": 0.5337,
      "step": 95
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019903574131932702,
      "loss": 0.5378,
      "step": 96
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019901558116398448,
      "loss": 0.5289,
      "step": 97
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001989952134772769,
      "loss": 0.529,
      "step": 98
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019897463830189388,
      "loss": 0.528,
      "step": 99
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019895385568095982,
      "loss": 0.5201,
      "step": 100
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000198932865658034,
      "loss": 0.537,
      "step": 101
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019891166827711037,
      "loss": 0.5262,
      "step": 102
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019889026358261758,
      "loss": 0.5379,
      "step": 103
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019886865161941866,
      "loss": 0.531,
      "step": 104
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019884683243281116,
      "loss": 0.525,
      "step": 105
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001988248060685269,
      "loss": 0.5221,
      "step": 106
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019880257257273197,
      "loss": 0.5204,
      "step": 107
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019878013199202662,
      "loss": 0.5289,
      "step": 108
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001987574843734451,
      "loss": 0.518,
      "step": 109
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019873462976445553,
      "loss": 0.5253,
      "step": 110
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019871156821296007,
      "loss": 0.5255,
      "step": 111
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019868829976729443,
      "loss": 0.5276,
      "step": 112
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019866482447622802,
      "loss": 0.5192,
      "step": 113
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019864114238896384,
      "loss": 0.5165,
      "step": 114
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019861725355513823,
      "loss": 0.5185,
      "step": 115
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019859315802482096,
      "loss": 0.5205,
      "step": 116
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001985688558485149,
      "loss": 0.5187,
      "step": 117
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001985443470771562,
      "loss": 0.5214,
      "step": 118
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019851963176211387,
      "loss": 0.5195,
      "step": 119
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019849470995518992,
      "loss": 0.5286,
      "step": 120
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001984695817086191,
      "loss": 0.5184,
      "step": 121
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001984442470750689,
      "loss": 0.5131,
      "step": 122
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019841870610763938,
      "loss": 0.5225,
      "step": 123
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019839295885986296,
      "loss": 0.51,
      "step": 124
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019836700538570457,
      "loss": 0.5201,
      "step": 125
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019834084573956128,
      "loss": 0.517,
      "step": 126
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001983144799762623,
      "loss": 0.5176,
      "step": 127
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019828790815106887,
      "loss": 0.5255,
      "step": 128
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001982611303196741,
      "loss": 0.5221,
      "step": 129
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001982341465382029,
      "loss": 0.5107,
      "step": 130
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019820695686321185,
      "loss": 0.5196,
      "step": 131
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019817956135168908,
      "loss": 0.513,
      "step": 132
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019815196006105402,
      "loss": 0.5175,
      "step": 133
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001981241530491576,
      "loss": 0.5188,
      "step": 134
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019809614037428176,
      "loss": 0.5123,
      "step": 135
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019806792209513968,
      "loss": 0.5089,
      "step": 136
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001980394982708752,
      "loss": 0.5117,
      "step": 137
    },
    {
      "epoch": 0.63,
      "eval_loss": 0.5121904611587524,
      "eval_runtime": 28.8865,
      "eval_samples_per_second": 6.924,
      "eval_steps_per_second": 0.865,
      "step": 137
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00019801086896106327,
      "loss": 0.5101,
      "step": 138
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00019798203422570932,
      "loss": 0.5079,
      "step": 139
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00019795299412524945,
      "loss": 0.5082,
      "step": 140
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00019792374872055018,
      "loss": 0.5159,
      "step": 141
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00019789429807290823,
      "loss": 0.5135,
      "step": 142
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00019786464224405065,
      "loss": 0.5111,
      "step": 143
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00019783478129613448,
      "loss": 0.51,
      "step": 144
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00019780471529174664,
      "loss": 0.5014,
      "step": 145
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00019777444429390387,
      "loss": 0.5169,
      "step": 146
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00019774396836605255,
      "loss": 0.5144,
      "step": 147
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00019771328757206864,
      "loss": 0.5075,
      "step": 148
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00019768240197625742,
      "loss": 0.5074,
      "step": 149
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00019765131164335345,
      "loss": 0.5056,
      "step": 150
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001976200166385204,
      "loss": 0.5025,
      "step": 151
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001975885170273509,
      "loss": 0.5089,
      "step": 152
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019755681287586652,
      "loss": 0.5077,
      "step": 153
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019752490425051743,
      "loss": 0.5185,
      "step": 154
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.5096,
      "step": 155
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001974604738461686,
      "loss": 0.5089,
      "step": 156
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00019742795220221155,
      "loss": 0.5075,
      "step": 157
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00019739522635447488,
      "loss": 0.509,
      "step": 158
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00019736229637155018,
      "loss": 0.5009,
      "step": 159
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.000197329162322457,
      "loss": 0.502,
      "step": 160
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001972958242766425,
      "loss": 0.5106,
      "step": 161
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00019726228230398146,
      "loss": 0.4997,
      "step": 162
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00019722853647477598,
      "loss": 0.4935,
      "step": 163
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001971945868597556,
      "loss": 0.5075,
      "step": 164
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00019716043353007693,
      "loss": 0.5019,
      "step": 165
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00019712607655732338,
      "loss": 0.5011,
      "step": 166
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00019709151601350546,
      "loss": 0.5019,
      "step": 167
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00019705675197106016,
      "loss": 0.5005,
      "step": 168
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001970217845028511,
      "loss": 0.5074,
      "step": 169
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00019698661368216817,
      "loss": 0.4961,
      "step": 170
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00019695123958272758,
      "loss": 0.499,
      "step": 171
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00019691566227867153,
      "loss": 0.4997,
      "step": 172
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00019687988184456814,
      "loss": 0.502,
      "step": 173
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00019684389835541129,
      "loss": 0.5003,
      "step": 174
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00019680771188662044,
      "loss": 0.4884,
      "step": 175
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001967713225140405,
      "loss": 0.4958,
      "step": 176
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001967347303139417,
      "loss": 0.4957,
      "step": 177
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00019669793536301926,
      "loss": 0.5016,
      "step": 178
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019666093773839345,
      "loss": 0.5025,
      "step": 179
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019662373751760934,
      "loss": 0.5035,
      "step": 180
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00019658633477863662,
      "loss": 0.5028,
      "step": 181
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00019654872959986937,
      "loss": 0.5011,
      "step": 182
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00019651092206012603,
      "loss": 0.4915,
      "step": 183
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00019647291223864928,
      "loss": 0.494,
      "step": 184
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001964347002151056,
      "loss": 0.5037,
      "step": 185
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00019639628606958533,
      "loss": 0.4965,
      "step": 186
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00019635766988260254,
      "loss": 0.4897,
      "step": 187
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001963188517350946,
      "loss": 0.4952,
      "step": 188
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00019627983170842234,
      "loss": 0.4903,
      "step": 189
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00019624060988436966,
      "loss": 0.4982,
      "step": 190
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00019620118634514335,
      "loss": 0.4999,
      "step": 191
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00019616156117337305,
      "loss": 0.4917,
      "step": 192
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00019612173445211106,
      "loss": 0.4878,
      "step": 193
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00019608170626483199,
      "loss": 0.4946,
      "step": 194
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00019604147669543282,
      "loss": 0.4968,
      "step": 195
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001960010458282326,
      "loss": 0.4891,
      "step": 196
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00019596041374797218,
      "loss": 0.4952,
      "step": 197
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00019591958053981432,
      "loss": 0.4928,
      "step": 198
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00019587854628934319,
      "loss": 0.4998,
      "step": 199
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001958373110825644,
      "loss": 0.496,
      "step": 200
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00019579587500590472,
      "loss": 0.4926,
      "step": 201
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00019575423814621198,
      "loss": 0.4939,
      "step": 202
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001957124005907548,
      "loss": 0.495,
      "step": 203
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00019567036242722249,
      "loss": 0.4962,
      "step": 204
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00019562812374372473,
      "loss": 0.4931,
      "step": 205
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00019558568462879158,
      "loss": 0.4843,
      "step": 206
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00019554304517137316,
      "loss": 0.4963,
      "step": 207
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00019550020546083949,
      "loss": 0.4979,
      "step": 208
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001954571655869803,
      "loss": 0.4925,
      "step": 209
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00019541392564000488,
      "loss": 0.4953,
      "step": 210
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00019537048571054185,
      "loss": 0.4921,
      "step": 211
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.000195326845889639,
      "loss": 0.4917,
      "step": 212
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.000195283006268763,
      "loss": 0.4956,
      "step": 213
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00019523896693979936,
      "loss": 0.4901,
      "step": 214
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001951947279950522,
      "loss": 0.4865,
      "step": 215
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.000195150289527244,
      "loss": 0.4871,
      "step": 216
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.4948,
      "step": 217
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00019506081439542495,
      "loss": 0.4861,
      "step": 218
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00019501577791894922,
      "loss": 0.4852,
      "step": 219
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00019497054229448223,
      "loss": 0.4754,
      "step": 220
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00019492510761683537,
      "loss": 0.4892,
      "step": 221
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00019487947398123736,
      "loss": 0.4894,
      "step": 222
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00019483364148333384,
      "loss": 0.4906,
      "step": 223
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00019478761021918728,
      "loss": 0.4932,
      "step": 224
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00019474138028527675,
      "loss": 0.4863,
      "step": 225
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00019469495177849768,
      "loss": 0.494,
      "step": 226
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00019464832479616182,
      "loss": 0.4893,
      "step": 227
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00019460149943599674,
      "loss": 0.4942,
      "step": 228
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00019455447579614594,
      "loss": 0.4893,
      "step": 229
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001945072539751685,
      "loss": 0.4855,
      "step": 230
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00019445983407203872,
      "loss": 0.4828,
      "step": 231
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00019441221618614628,
      "loss": 0.4928,
      "step": 232
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00019436440041729569,
      "loss": 0.483,
      "step": 233
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00019431638686570623,
      "loss": 0.4854,
      "step": 234
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00019426817563201177,
      "loss": 0.4906,
      "step": 235
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00019421976681726046,
      "loss": 0.4856,
      "step": 236
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00019417116052291458,
      "loss": 0.4872,
      "step": 237
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00019412235685085035,
      "loss": 0.4786,
      "step": 238
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001940733559033576,
      "loss": 0.49,
      "step": 239
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00019402415778313977,
      "loss": 0.4899,
      "step": 240
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00019397476259331344,
      "loss": 0.4839,
      "step": 241
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001939251704374083,
      "loss": 0.4817,
      "step": 242
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001938753814193669,
      "loss": 0.4818,
      "step": 243
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00019382539564354433,
      "loss": 0.4865,
      "step": 244
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00019377521321470805,
      "loss": 0.4935,
      "step": 245
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00019372483423803783,
      "loss": 0.4879,
      "step": 246
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00019367425881912525,
      "loss": 0.4833,
      "step": 247
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00019362348706397373,
      "loss": 0.4782,
      "step": 248
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00019357251907899814,
      "loss": 0.4805,
      "step": 249
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00019352135497102463,
      "loss": 0.4881,
      "step": 250
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00019346999484729047,
      "loss": 0.4766,
      "step": 251
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00019341843881544372,
      "loss": 0.4799,
      "step": 252
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00019336668698354304,
      "loss": 0.4875,
      "step": 253
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00019331473946005754,
      "loss": 0.4834,
      "step": 254
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00019326259635386644,
      "loss": 0.4852,
      "step": 255
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00019321025777425892,
      "loss": 0.477,
      "step": 256
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001931577238309338,
      "loss": 0.4849,
      "step": 257
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00019310499463399947,
      "loss": 0.4854,
      "step": 258
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00019305207029397348,
      "loss": 0.4869,
      "step": 259
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001929989509217824,
      "loss": 0.4772,
      "step": 260
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00019294563662876165,
      "loss": 0.4867,
      "step": 261
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00019289212752665507,
      "loss": 0.4806,
      "step": 262
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00019283842372761493,
      "loss": 0.4839,
      "step": 263
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00019278452534420145,
      "loss": 0.4857,
      "step": 264
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00019273043248938288,
      "loss": 0.477,
      "step": 265
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00019267614527653488,
      "loss": 0.4868,
      "step": 266
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00019262166381944052,
      "loss": 0.485,
      "step": 267
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019256698823229008,
      "loss": 0.485,
      "step": 268
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019251211862968059,
      "loss": 0.4824,
      "step": 269
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0001924570551266159,
      "loss": 0.4858,
      "step": 270
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00019240179783850612,
      "loss": 0.4793,
      "step": 271
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00019234634688116757,
      "loss": 0.4762,
      "step": 272
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00019229070237082252,
      "loss": 0.4808,
      "step": 273
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00019223486442409882,
      "loss": 0.4704,
      "step": 274
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00019217883315802991,
      "loss": 0.4733,
      "step": 275
    },
    {
      "epoch": 1.63,
      "eval_loss": 0.4869104027748108,
      "eval_runtime": 28.3583,
      "eval_samples_per_second": 7.053,
      "eval_steps_per_second": 0.882,
      "step": 275
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00019212260869005428,
      "loss": 0.4777,
      "step": 276
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001920661911380154,
      "loss": 0.4813,
      "step": 277
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00019200958062016144,
      "loss": 0.48,
      "step": 278
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001919527772551451,
      "loss": 0.4831,
      "step": 279
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00019189578116202307,
      "loss": 0.4649,
      "step": 280
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0001918385924602562,
      "loss": 0.4728,
      "step": 281
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00019178121126970895,
      "loss": 0.4836,
      "step": 282
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001917236377106492,
      "loss": 0.4833,
      "step": 283
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00019166587190374808,
      "loss": 0.4733,
      "step": 284
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00019160791397007957,
      "loss": 0.483,
      "step": 285
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001915497640311205,
      "loss": 0.4731,
      "step": 286
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001914914222087499,
      "loss": 0.4825,
      "step": 287
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00019143288862524926,
      "loss": 0.4756,
      "step": 288
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00019137416340330175,
      "loss": 0.4796,
      "step": 289
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00019131524666599233,
      "loss": 0.479,
      "step": 290
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00019125613853680727,
      "loss": 0.4773,
      "step": 291
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00019119683913963417,
      "loss": 0.4782,
      "step": 292
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00019113734859876126,
      "loss": 0.48,
      "step": 293
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00019107766703887764,
      "loss": 0.4789,
      "step": 294
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00019101779458507263,
      "loss": 0.4792,
      "step": 295
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00019095773136283567,
      "loss": 0.4819,
      "step": 296
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00019089747749805608,
      "loss": 0.4715,
      "step": 297
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00019083703311702279,
      "loss": 0.4677,
      "step": 298
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00019077639834642388,
      "loss": 0.4688,
      "step": 299
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00019071557331334669,
      "loss": 0.4726,
      "step": 300
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00019065455814527718,
      "loss": 0.4777,
      "step": 301
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00019059335297009992,
      "loss": 0.4722,
      "step": 302
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00019053195791609765,
      "loss": 0.4827,
      "step": 303
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00019047037311195118,
      "loss": 0.4705,
      "step": 304
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00019040859868673887,
      "loss": 0.4725,
      "step": 305
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00019034663476993668,
      "loss": 0.4715,
      "step": 306
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00019028448149141766,
      "loss": 0.4779,
      "step": 307
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00019022213898145176,
      "loss": 0.4637,
      "step": 308
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00019015960737070556,
      "loss": 0.4794,
      "step": 309
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.4749,
      "step": 310
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00019003397737151989,
      "loss": 0.4724,
      "step": 311
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0001899708792463942,
      "loss": 0.4665,
      "step": 312
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00018990759254711517,
      "loss": 0.4668,
      "step": 313
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001898441174063283,
      "loss": 0.475,
      "step": 314
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00018978045395707418,
      "loss": 0.4661,
      "step": 315
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001897166023327879,
      "loss": 0.4732,
      "step": 316
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00018965256266729913,
      "loss": 0.4749,
      "step": 317
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00018958833509483155,
      "loss": 0.4762,
      "step": 318
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00018952391975000268,
      "loss": 0.4732,
      "step": 319
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00018945931676782373,
      "loss": 0.4773,
      "step": 320
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00018939452628369898,
      "loss": 0.4759,
      "step": 321
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00018932954843342591,
      "loss": 0.4681,
      "step": 322
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00018926438335319462,
      "loss": 0.4693,
      "step": 323
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00018919903117958756,
      "loss": 0.4684,
      "step": 324
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001891334920495795,
      "loss": 0.4665,
      "step": 325
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00018906776610053686,
      "loss": 0.4683,
      "step": 326
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00018900185347021776,
      "loss": 0.4708,
      "step": 327
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00018893575429677157,
      "loss": 0.4659,
      "step": 328
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00018886946871873856,
      "loss": 0.466,
      "step": 329
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0001888029968750498,
      "loss": 0.4724,
      "step": 330
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00018873633890502674,
      "loss": 0.4686,
      "step": 331
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00018866949494838084,
      "loss": 0.469,
      "step": 332
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0001886024651452136,
      "loss": 0.4659,
      "step": 333
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00018853524963601575,
      "loss": 0.4707,
      "step": 334
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001884678485616675,
      "loss": 0.4687,
      "step": 335
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00018840026206343784,
      "loss": 0.471,
      "step": 336
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00018833249028298455,
      "loss": 0.4644,
      "step": 337
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00018826453336235358,
      "loss": 0.4708,
      "step": 338
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.000188196391443979,
      "loss": 0.4664,
      "step": 339
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00018812806467068268,
      "loss": 0.4771,
      "step": 340
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0001880595531856738,
      "loss": 0.4685,
      "step": 341
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00018799085713254888,
      "loss": 0.4635,
      "step": 342
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0001879219766552911,
      "loss": 0.4751,
      "step": 343
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0001878529118982703,
      "loss": 0.469,
      "step": 344
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00018778366300624245,
      "loss": 0.4735,
      "step": 345
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001877142301243496,
      "loss": 0.4617,
      "step": 346
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00018764461339811935,
      "loss": 0.4664,
      "step": 347
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0001875748129734646,
      "loss": 0.4717,
      "step": 348
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00018750482899668332,
      "loss": 0.4676,
      "step": 349
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00018743466161445823,
      "loss": 0.4665,
      "step": 350
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00018736431097385634,
      "loss": 0.4635,
      "step": 351
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0001872937772223289,
      "loss": 0.4676,
      "step": 352
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0001872230605077108,
      "loss": 0.4666,
      "step": 353
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00018715216097822058,
      "loss": 0.4673,
      "step": 354
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00018708107878245977,
      "loss": 0.4632,
      "step": 355
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00018700981406941298,
      "loss": 0.4659,
      "step": 356
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0001869383669884471,
      "loss": 0.4683,
      "step": 357
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00018686673768931154,
      "loss": 0.4715,
      "step": 358
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00018679492632213735,
      "loss": 0.4748,
      "step": 359
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00018672293303743738,
      "loss": 0.4596,
      "step": 360
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00018665075798610567,
      "loss": 0.4586,
      "step": 361
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0001865784013194173,
      "loss": 0.4609,
      "step": 362
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00018650586318902802,
      "loss": 0.467,
      "step": 363
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00018643314374697378,
      "loss": 0.4602,
      "step": 364
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00018636024314567067,
      "loss": 0.4709,
      "step": 365
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001862871615379145,
      "loss": 0.471,
      "step": 366
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00018621389907688037,
      "loss": 0.4605,
      "step": 367
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0001861404559161225,
      "loss": 0.468,
      "step": 368
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00018606683220957383,
      "loss": 0.4632,
      "step": 369
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00018599302811154572,
      "loss": 0.4633,
      "step": 370
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00018591904377672757,
      "loss": 0.4692,
      "step": 371
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00018584487936018661,
      "loss": 0.4693,
      "step": 372
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00018577053501736752,
      "loss": 0.4566,
      "step": 373
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001856960109040921,
      "loss": 0.4679,
      "step": 374
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00018562130717655878,
      "loss": 0.4611,
      "step": 375
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0001855464239913427,
      "loss": 0.4654,
      "step": 376
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.000185471361505395,
      "loss": 0.4626,
      "step": 377
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00018539611987604258,
      "loss": 0.4667,
      "step": 378
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001853206992609879,
      "loss": 0.4624,
      "step": 379
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00018524509981830852,
      "loss": 0.4602,
      "step": 380
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0001851693217064569,
      "loss": 0.4644,
      "step": 381
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00018509336508425986,
      "loss": 0.4664,
      "step": 382
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0001850172301109184,
      "loss": 0.4665,
      "step": 383
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00018494091694600738,
      "loss": 0.4629,
      "step": 384
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00018486442574947511,
      "loss": 0.4609,
      "step": 385
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00018478775668164305,
      "loss": 0.4593,
      "step": 386
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00018471090990320547,
      "loss": 0.4625,
      "step": 387
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0001846338855752291,
      "loss": 0.4573,
      "step": 388
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00018455668385915284,
      "loss": 0.4578,
      "step": 389
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00018447930491678733,
      "loss": 0.4649,
      "step": 390
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0001844017489103147,
      "loss": 0.4641,
      "step": 391
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00018432401600228823,
      "loss": 0.4545,
      "step": 392
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0001842461063556319,
      "loss": 0.4574,
      "step": 393
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00018416802013364016,
      "loss": 0.4604,
      "step": 394
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00018408975749997759,
      "loss": 0.4628,
      "step": 395
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00018401131861867846,
      "loss": 0.469,
      "step": 396
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0001839327036541465,
      "loss": 0.4679,
      "step": 397
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00018385391277115444,
      "loss": 0.464,
      "step": 398
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.00018377494613484378,
      "loss": 0.4658,
      "step": 399
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.00018369580391072433,
      "loss": 0.4631,
      "step": 400
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.00018361648626467406,
      "loss": 0.4567,
      "step": 401
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0001835369933629384,
      "loss": 0.4617,
      "step": 402
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.00018345732537213027,
      "loss": 0.4632,
      "step": 403
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00018337748245922955,
      "loss": 0.4609,
      "step": 404
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00018329746479158265,
      "loss": 0.4571,
      "step": 405
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0001832172725369024,
      "loss": 0.4662,
      "step": 406
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.00018313690586326743,
      "loss": 0.4649,
      "step": 407
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00018305636493912202,
      "loss": 0.4582,
      "step": 408
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00018297564993327562,
      "loss": 0.4627,
      "step": 409
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.00018289476101490256,
      "loss": 0.4547,
      "step": 410
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0001828136983535417,
      "loss": 0.4623,
      "step": 411
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00018273246211909604,
      "loss": 0.4549,
      "step": 412
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00018265105248183242,
      "loss": 0.4585,
      "step": 413
    },
    {
      "epoch": 2.63,
      "eval_loss": 0.4760552644729614,
      "eval_runtime": 28.2621,
      "eval_samples_per_second": 7.077,
      "eval_steps_per_second": 0.885,
      "step": 413
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.000182569469612381,
      "loss": 0.4544,
      "step": 414
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.00018248771368173524,
      "loss": 0.4522,
      "step": 415
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.00018240578486125112,
      "loss": 0.4587,
      "step": 416
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00018232368332264708,
      "loss": 0.4565,
      "step": 417
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00018224140923800354,
      "loss": 0.4661,
      "step": 418
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0001821589627797626,
      "loss": 0.4553,
      "step": 419
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.00018207634412072764,
      "loss": 0.4566,
      "step": 420
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.00018199355343406296,
      "loss": 0.4582,
      "step": 421
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.00018191059089329333,
      "loss": 0.4577,
      "step": 422
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.00018182745667230394,
      "loss": 0.4609,
      "step": 423
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.00018174415094533957,
      "loss": 0.4656,
      "step": 424
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0001816606738870046,
      "loss": 0.4561,
      "step": 425
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.00018157702567226248,
      "loss": 0.4582,
      "step": 426
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.00018149320647643541,
      "loss": 0.4552,
      "step": 427
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.00018140921647520392,
      "loss": 0.4623,
      "step": 428
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.00018132505584460658,
      "loss": 0.4602,
      "step": 429
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.00018124072476103956,
      "loss": 0.4647,
      "step": 430
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.00018115622340125631,
      "loss": 0.4606,
      "step": 431
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.00018107155194236718,
      "loss": 0.4661,
      "step": 432
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.00018098671056183897,
      "loss": 0.4525,
      "step": 433
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.4534,
      "step": 434
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.00018081651874751327,
      "loss": 0.4552,
      "step": 435
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.00018073116867042862,
      "loss": 0.4536,
      "step": 436
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.00018064564938513012,
      "loss": 0.4575,
      "step": 437
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.00018055996107086157,
      "loss": 0.4505,
      "step": 438
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0001804741039072211,
      "loss": 0.4557,
      "step": 439
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.00018038807807416068,
      "loss": 0.4523,
      "step": 440
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.00018030188375198593,
      "loss": 0.4535,
      "step": 441
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.00018021552112135552,
      "loss": 0.4579,
      "step": 442
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.00018012899036328093,
      "loss": 0.4509,
      "step": 443
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.00018004229165912596,
      "loss": 0.4583,
      "step": 444
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.00017995542519060647,
      "loss": 0.4574,
      "step": 445
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00017986839113978996,
      "loss": 0.451,
      "step": 446
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00017978118968909508,
      "loss": 0.4511,
      "step": 447
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.0001796938210212915,
      "loss": 0.4586,
      "step": 448
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.00017960628531949927,
      "loss": 0.4465,
      "step": 449
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.00017951858276718844,
      "loss": 0.4502,
      "step": 450
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.00017943071354817897,
      "loss": 0.4553,
      "step": 451
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.00017934267784664002,
      "loss": 0.456,
      "step": 452
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.00017925447584708973,
      "loss": 0.448,
      "step": 453
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.00017916610773439473,
      "loss": 0.4509,
      "step": 454
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.00017907757369376985,
      "loss": 0.4544,
      "step": 455
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0001789888739107778,
      "loss": 0.4512,
      "step": 456
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.00017890000857132853,
      "loss": 0.4561,
      "step": 457
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.00017881097786167898,
      "loss": 0.462,
      "step": 458
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.00017872178196843286,
      "loss": 0.4512,
      "step": 459
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.00017863242107853995,
      "loss": 0.455,
      "step": 460
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.00017854289537929587,
      "loss": 0.4562,
      "step": 461
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.00017845320505834175,
      "loss": 0.4512,
      "step": 462
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.00017836335030366367,
      "loss": 0.4532,
      "step": 463
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.00017827333130359242,
      "loss": 0.4526,
      "step": 464
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.000178183148246803,
      "loss": 0.4487,
      "step": 465
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.00017809280132231425,
      "loss": 0.449,
      "step": 466
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.00017800229071948854,
      "loss": 0.4507,
      "step": 467
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.00017791161662803124,
      "loss": 0.4473,
      "step": 468
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0001778207792379904,
      "loss": 0.4518,
      "step": 469
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0001777297787397563,
      "loss": 0.452,
      "step": 470
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0001776386153240612,
      "loss": 0.4549,
      "step": 471
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.00017754728918197864,
      "loss": 0.4459,
      "step": 472
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.00017745580050492344,
      "loss": 0.4518,
      "step": 473
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.00017736414948465087,
      "loss": 0.4495,
      "step": 474
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.00017727233631325664,
      "loss": 0.4539,
      "step": 475
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.0001771803611831762,
      "loss": 0.4498,
      "step": 476
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.00017708822428718458,
      "loss": 0.4586,
      "step": 477
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.00017699592581839574,
      "loss": 0.4531,
      "step": 478
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.00017690346597026233,
      "loss": 0.4536,
      "step": 479
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.00017681084493657525,
      "loss": 0.4485,
      "step": 480
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.00017671806291146325,
      "loss": 0.4497,
      "step": 481
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.00017662512008939247,
      "loss": 0.448,
      "step": 482
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.00017653201666516615,
      "loss": 0.4465,
      "step": 483
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.00017643875283392406,
      "loss": 0.4516,
      "step": 484
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0001763453287911422,
      "loss": 0.4529,
      "step": 485
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00017625174473263235,
      "loss": 0.4552,
      "step": 486
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.00017615800085454171,
      "loss": 0.4474,
      "step": 487
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.00017606409735335246,
      "loss": 0.4542,
      "step": 488
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.00017597003442588132,
      "loss": 0.4471,
      "step": 489
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.0001758758122692791,
      "loss": 0.4474,
      "step": 490
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.00017578143108103048,
      "loss": 0.4514,
      "step": 491
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0001756868910589533,
      "loss": 0.4539,
      "step": 492
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.00017559219240119846,
      "loss": 0.4504,
      "step": 493
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.00017549733530624928,
      "loss": 0.4444,
      "step": 494
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.00017540231997292114,
      "loss": 0.4485,
      "step": 495
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.00017530714660036112,
      "loss": 0.4517,
      "step": 496
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.00017521181538804746,
      "loss": 0.4478,
      "step": 497
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.00017511632653578936,
      "loss": 0.4464,
      "step": 498
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.00017502068024372633,
      "loss": 0.4463,
      "step": 499
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.00017492487671232784,
      "loss": 0.4464,
      "step": 500
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.00017482891614239304,
      "loss": 0.4496,
      "step": 501
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.0001747327987350501,
      "loss": 0.4479,
      "step": 502
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.00017463652469175599,
      "loss": 0.444,
      "step": 503
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.00017454009421429597,
      "loss": 0.4507,
      "step": 504
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.00017444350750478316,
      "loss": 0.4502,
      "step": 505
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0001743467647656581,
      "loss": 0.4535,
      "step": 506
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.00017424986619968844,
      "loss": 0.444,
      "step": 507
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.00017415281200996842,
      "loss": 0.4498,
      "step": 508
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.00017405560239991833,
      "loss": 0.454,
      "step": 509
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.00017395823757328444,
      "loss": 0.4479,
      "step": 510
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.00017386071773413817,
      "loss": 0.4431,
      "step": 511
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.00017376304308687587,
      "loss": 0.4455,
      "step": 512
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0001736652138362184,
      "loss": 0.4512,
      "step": 513
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.00017356723018721067,
      "loss": 0.4504,
      "step": 514
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.00017346909234522109,
      "loss": 0.4422,
      "step": 515
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.00017337080051594138,
      "loss": 0.4535,
      "step": 516
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.00017327235490538598,
      "loss": 0.4457,
      "step": 517
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.00017317375571989158,
      "loss": 0.4519,
      "step": 518
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.00017307500316611686,
      "loss": 0.446,
      "step": 519
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.00017297609745104184,
      "loss": 0.4501,
      "step": 520
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.00017287703878196762,
      "loss": 0.4427,
      "step": 521
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0001727778273665159,
      "loss": 0.4429,
      "step": 522
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.00017267846341262848,
      "loss": 0.4423,
      "step": 523
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0001725789471285669,
      "loss": 0.4458,
      "step": 524
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.000172479278722912,
      "loss": 0.4452,
      "step": 525
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.0001723794584045634,
      "loss": 0.4426,
      "step": 526
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.00017227948638273916,
      "loss": 0.4484,
      "step": 527
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0001721793628669753,
      "loss": 0.4431,
      "step": 528
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.00017207908806712535,
      "loss": 0.4424,
      "step": 529
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0001719786621933599,
      "loss": 0.4469,
      "step": 530
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.00017187808545616627,
      "loss": 0.4492,
      "step": 531
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.00017177735806634789,
      "loss": 0.4464,
      "step": 532
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.00017167648023502395,
      "loss": 0.4395,
      "step": 533
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.0001715754521736291,
      "loss": 0.4483,
      "step": 534
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.00017147427409391265,
      "loss": 0.4494,
      "step": 535
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.00017137294620793848,
      "loss": 0.4474,
      "step": 536
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.00017127146872808447,
      "loss": 0.4502,
      "step": 537
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.00017116984186704194,
      "loss": 0.4417,
      "step": 538
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.00017106806583781534,
      "loss": 0.4472,
      "step": 539
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.00017096614085372185,
      "loss": 0.4442,
      "step": 540
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.00017086406712839072,
      "loss": 0.4437,
      "step": 541
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.0001707618448757631,
      "loss": 0.4473,
      "step": 542
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.00017065947431009126,
      "loss": 0.4435,
      "step": 543
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.00017055695564593853,
      "loss": 0.4458,
      "step": 544
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.0001704542890981785,
      "loss": 0.4442,
      "step": 545
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.00017035147488199482,
      "loss": 0.4444,
      "step": 546
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.00017024851321288052,
      "loss": 0.4455,
      "step": 547
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.0001701454043066378,
      "loss": 0.4467,
      "step": 548
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.00017004214837937738,
      "loss": 0.4439,
      "step": 549
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.00016993874564751822,
      "loss": 0.4376,
      "step": 550
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.00016983519632778686,
      "loss": 0.4408,
      "step": 551
    },
    {
      "epoch": 3.63,
      "eval_loss": 0.4704599976539612,
      "eval_runtime": 28.2725,
      "eval_samples_per_second": 7.074,
      "eval_steps_per_second": 0.884,
      "step": 551
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00016973150063721718,
      "loss": 0.4355,
      "step": 552
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.0001696276587931498,
      "loss": 0.4467,
      "step": 553
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.00016952367101323162,
      "loss": 0.438,
      "step": 554
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.00016941953751541553,
      "loss": 0.4454,
      "step": 555
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.00016931525851795977,
      "loss": 0.4458,
      "step": 556
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0001692108342394275,
      "loss": 0.4359,
      "step": 557
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.00016910626489868649,
      "loss": 0.4477,
      "step": 558
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.00016900155071490844,
      "loss": 0.4363,
      "step": 559
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.00016889669190756868,
      "loss": 0.448,
      "step": 560
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.00016879168869644566,
      "loss": 0.4406,
      "step": 561
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.00016868654130162056,
      "loss": 0.446,
      "step": 562
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.00016858124994347665,
      "loss": 0.4448,
      "step": 563
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.00016847581484269897,
      "loss": 0.4432,
      "step": 564
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.00016837023622027388,
      "loss": 0.4376,
      "step": 565
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.00016826451429748852,
      "loss": 0.4498,
      "step": 566
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.00016815864929593043,
      "loss": 0.4434,
      "step": 567
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00016805264143748694,
      "loss": 0.4466,
      "step": 568
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00016794649094434486,
      "loss": 0.4378,
      "step": 569
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00016784019803899,
      "loss": 0.4401,
      "step": 570
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.00016773376294420652,
      "loss": 0.454,
      "step": 571
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.00016762718588307678,
      "loss": 0.4412,
      "step": 572
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.00016752046707898055,
      "loss": 0.443,
      "step": 573
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.00016741360675559473,
      "loss": 0.429,
      "step": 574
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00016730660513689292,
      "loss": 0.4325,
      "step": 575
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0001671994624471447,
      "loss": 0.4462,
      "step": 576
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.00016709217891091547,
      "loss": 0.4417,
      "step": 577
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.00016698475475306578,
      "loss": 0.4397,
      "step": 578
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.00016687719019875088,
      "loss": 0.4433,
      "step": 579
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0001667694854734204,
      "loss": 0.4382,
      "step": 580
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.00016666164080281765,
      "loss": 0.4325,
      "step": 581
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.00016655365641297929,
      "loss": 0.4425,
      "step": 582
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.00016644553253023484,
      "loss": 0.439,
      "step": 583
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.00016633726938120616,
      "loss": 0.4433,
      "step": 584
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.00016622886719280705,
      "loss": 0.4399,
      "step": 585
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.0001661203261922427,
      "loss": 0.4387,
      "step": 586
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.00016601164660700918,
      "loss": 0.438,
      "step": 587
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.00016590282866489319,
      "loss": 0.4402,
      "step": 588
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.00016579387259397127,
      "loss": 0.4404,
      "step": 589
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.0001656847786226095,
      "loss": 0.4344,
      "step": 590
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.00016557554697946308,
      "loss": 0.4362,
      "step": 591
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.0001654661778934756,
      "loss": 0.4334,
      "step": 592
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.0001653566715938789,
      "loss": 0.4401,
      "step": 593
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.00016524702831019228,
      "loss": 0.4393,
      "step": 594
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.00016513724827222227,
      "loss": 0.4356,
      "step": 595
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.00016502733171006183,
      "loss": 0.4411,
      "step": 596
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0001649172788540903,
      "loss": 0.4404,
      "step": 597
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0001648070899349726,
      "loss": 0.4381,
      "step": 598
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.00016469676518365874,
      "loss": 0.4444,
      "step": 599
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.00016458630483138356,
      "loss": 0.4369,
      "step": 600
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.00016447570910966603,
      "loss": 0.4361,
      "step": 601
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.00016436497825030884,
      "loss": 0.4278,
      "step": 602
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.00016425411248539805,
      "loss": 0.4392,
      "step": 603
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.00016414311204730227,
      "loss": 0.438,
      "step": 604
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.0001640319771686725,
      "loss": 0.4361,
      "step": 605
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.00016392070808244155,
      "loss": 0.4302,
      "step": 606
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.00016380930502182345,
      "loss": 0.4342,
      "step": 607
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0001636977682203131,
      "loss": 0.4379,
      "step": 608
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0001635860979116856,
      "loss": 0.433,
      "step": 609
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.00016347429432999602,
      "loss": 0.4451,
      "step": 610
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.00016336235770957863,
      "loss": 0.4356,
      "step": 611
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.00016325028828504662,
      "loss": 0.4348,
      "step": 612
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.00016313808629129156,
      "loss": 0.4389,
      "step": 613
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0001630257519634828,
      "loss": 0.4287,
      "step": 614
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.00016291328553706704,
      "loss": 0.4381,
      "step": 615
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.00016280068724776797,
      "loss": 0.439,
      "step": 616
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.00016268795733158552,
      "loss": 0.4384,
      "step": 617
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.00016257509602479563,
      "loss": 0.4389,
      "step": 618
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.00016246210356394953,
      "loss": 0.4391,
      "step": 619
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.4393,
      "step": 620
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.00016223572612766773,
      "loss": 0.428,
      "step": 621
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.00016212234162670704,
      "loss": 0.4375,
      "step": 622
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.00016200882692063917,
      "loss": 0.4392,
      "step": 623
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.00016189518224738486,
      "loss": 0.4342,
      "step": 624
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0001617814078451373,
      "loss": 0.4408,
      "step": 625
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0001616675039523615,
      "loss": 0.4375,
      "step": 626
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.000161553470807794,
      "loss": 0.4405,
      "step": 627
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.00016143930865044213,
      "loss": 0.4301,
      "step": 628
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.00016132501771958367,
      "loss": 0.432,
      "step": 629
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.0001612105982547663,
      "loss": 0.4318,
      "step": 630
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0001610960504958071,
      "loss": 0.4351,
      "step": 631
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0001609813746827921,
      "loss": 0.4364,
      "step": 632
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.00016086657105607562,
      "loss": 0.4346,
      "step": 633
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.00016075163985627993,
      "loss": 0.4317,
      "step": 634
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.0001606365813242947,
      "loss": 0.4321,
      "step": 635
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.0001605213957012764,
      "loss": 0.4314,
      "step": 636
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.00016040608322864808,
      "loss": 0.4389,
      "step": 637
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.00016029064414809838,
      "loss": 0.4367,
      "step": 638
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.00016017507870158147,
      "loss": 0.4361,
      "step": 639
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.00016005938713131642,
      "loss": 0.4345,
      "step": 640
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0001599435696797865,
      "loss": 0.4337,
      "step": 641
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.00015982762658973894,
      "loss": 0.4413,
      "step": 642
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.00015971155810418422,
      "loss": 0.4385,
      "step": 643
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.0001595953644663957,
      "loss": 0.4299,
      "step": 644
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.00015947904591990907,
      "loss": 0.4294,
      "step": 645
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.00015936260270852173,
      "loss": 0.4328,
      "step": 646
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.00015924603507629244,
      "loss": 0.4281,
      "step": 647
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0001591293432675407,
      "loss": 0.4418,
      "step": 648
    },
    {
      "epoch": 4.45,
      "learning_rate": 0.0001590125275268464,
      "loss": 0.4322,
      "step": 649
    },
    {
      "epoch": 4.45,
      "learning_rate": 0.00015889558809904902,
      "loss": 0.4346,
      "step": 650
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.4282,
      "step": 651
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.00015866133916279886,
      "loss": 0.4389,
      "step": 652
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.00015854403014531937,
      "loss": 0.4303,
      "step": 653
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.0001584265984226823,
      "loss": 0.4343,
      "step": 654
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0001583090442410182,
      "loss": 0.4348,
      "step": 655
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0001581913678467144,
      "loss": 0.4332,
      "step": 656
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0001580735694864143,
      "loss": 0.4269,
      "step": 657
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.000157955649407017,
      "loss": 0.4343,
      "step": 658
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.00015783760785567665,
      "loss": 0.4393,
      "step": 659
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.00015771944507980207,
      "loss": 0.4323,
      "step": 660
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0001576011613270561,
      "loss": 0.4332,
      "step": 661
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.00015748275684535515,
      "loss": 0.4323,
      "step": 662
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.0001573642318828687,
      "loss": 0.4292,
      "step": 663
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.00015724558668801875,
      "loss": 0.4303,
      "step": 664
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.00015712682150947923,
      "loss": 0.4311,
      "step": 665
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.00015700793659617567,
      "loss": 0.4302,
      "step": 666
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.00015688893219728445,
      "loss": 0.4311,
      "step": 667
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.00015676980856223248,
      "loss": 0.4349,
      "step": 668
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.00015665056594069647,
      "loss": 0.4277,
      "step": 669
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.00015653120458260263,
      "loss": 0.4334,
      "step": 670
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.00015641172473812592,
      "loss": 0.4297,
      "step": 671
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.00015629212665768978,
      "loss": 0.4328,
      "step": 672
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.00015617241059196534,
      "loss": 0.4362,
      "step": 673
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.00015605257679187113,
      "loss": 0.4316,
      "step": 674
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.00015593262550857233,
      "loss": 0.4365,
      "step": 675
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.00015581255699348046,
      "loss": 0.4316,
      "step": 676
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.00015569237149825265,
      "loss": 0.4273,
      "step": 677
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.00015557206927479137,
      "loss": 0.4296,
      "step": 678
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.00015545165057524358,
      "loss": 0.4362,
      "step": 679
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.00015533111565200044,
      "loss": 0.4323,
      "step": 680
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.00015521046475769674,
      "loss": 0.4344,
      "step": 681
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.00015508969814521025,
      "loss": 0.4291,
      "step": 682
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0001549688160676614,
      "loss": 0.4317,
      "step": 683
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.0001548478187784125,
      "loss": 0.4304,
      "step": 684
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.00015472670653106745,
      "loss": 0.4301,
      "step": 685
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.00015460547957947104,
      "loss": 0.4316,
      "step": 686
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.00015448413817770846,
      "loss": 0.4277,
      "step": 687
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.00015436268258010478,
      "loss": 0.4234,
      "step": 688
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.00015424111304122447,
      "loss": 0.4266,
      "step": 689
    },
    {
      "epoch": 4.63,
      "eval_loss": 0.46920087933540344,
      "eval_runtime": 28.2397,
      "eval_samples_per_second": 7.082,
      "eval_steps_per_second": 0.885,
      "step": 689
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0001541194298158708,
      "loss": 0.4297,
      "step": 690
    },
    {
      "epoch": 5.01,
      "learning_rate": 0.00015399763315908528,
      "loss": 0.4263,
      "step": 691
    },
    {
      "epoch": 5.01,
      "learning_rate": 0.0001538757233261472,
      "loss": 0.4264,
      "step": 692
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.00015375370057257306,
      "loss": 0.4329,
      "step": 693
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.00015363156515411602,
      "loss": 0.4166,
      "step": 694
    },
    {
      "epoch": 5.03,
      "learning_rate": 0.0001535093173267654,
      "loss": 0.4295,
      "step": 695
    },
    {
      "epoch": 5.03,
      "learning_rate": 0.00015338695734674605,
      "loss": 0.4378,
      "step": 696
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.00015326448547051805,
      "loss": 0.4306,
      "step": 697
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.00015314190195477584,
      "loss": 0.4321,
      "step": 698
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.00015301920705644792,
      "loss": 0.4264,
      "step": 699
    },
    {
      "epoch": 5.05,
      "learning_rate": 0.00015289640103269625,
      "loss": 0.4284,
      "step": 700
    },
    {
      "epoch": 5.05,
      "learning_rate": 0.00015277348414091568,
      "loss": 0.434,
      "step": 701
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.0001526504566387335,
      "loss": 0.4311,
      "step": 702
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.00015252731878400864,
      "loss": 0.4269,
      "step": 703
    },
    {
      "epoch": 5.07,
      "learning_rate": 0.00015240407083483163,
      "loss": 0.4259,
      "step": 704
    },
    {
      "epoch": 5.07,
      "learning_rate": 0.0001522807130495235,
      "loss": 0.4341,
      "step": 705
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.00015215724568663555,
      "loss": 0.4285,
      "step": 706
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.0001520336690049488,
      "loss": 0.4284,
      "step": 707
    },
    {
      "epoch": 5.09,
      "learning_rate": 0.0001519099832634734,
      "loss": 0.4388,
      "step": 708
    },
    {
      "epoch": 5.09,
      "learning_rate": 0.00015178618872144797,
      "loss": 0.4327,
      "step": 709
    },
    {
      "epoch": 5.09,
      "learning_rate": 0.00015166228563833934,
      "loss": 0.4287,
      "step": 710
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.00015153827427384173,
      "loss": 0.4297,
      "step": 711
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.00015141415488787626,
      "loss": 0.4266,
      "step": 712
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.00015128992774059063,
      "loss": 0.4245,
      "step": 713
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.00015116559309235825,
      "loss": 0.4289,
      "step": 714
    },
    {
      "epoch": 5.12,
      "learning_rate": 0.00015104115120377783,
      "loss": 0.4219,
      "step": 715
    },
    {
      "epoch": 5.12,
      "learning_rate": 0.00015091660233567305,
      "loss": 0.4281,
      "step": 716
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.0001507919467490916,
      "loss": 0.4241,
      "step": 717
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.00015066718470530495,
      "loss": 0.4243,
      "step": 718
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.00015054231646580764,
      "loss": 0.4218,
      "step": 719
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.00015041734229231688,
      "loss": 0.4294,
      "step": 720
    },
    {
      "epoch": 5.15,
      "learning_rate": 0.00015029226244677178,
      "loss": 0.4273,
      "step": 721
    },
    {
      "epoch": 5.15,
      "learning_rate": 0.0001501670771913331,
      "loss": 0.4258,
      "step": 722
    },
    {
      "epoch": 5.15,
      "learning_rate": 0.0001500417867883824,
      "loss": 0.4278,
      "step": 723
    },
    {
      "epoch": 5.16,
      "learning_rate": 0.0001499163915005216,
      "loss": 0.4312,
      "step": 724
    },
    {
      "epoch": 5.16,
      "learning_rate": 0.00014979089159057265,
      "loss": 0.4278,
      "step": 725
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.00014966528732157658,
      "loss": 0.422,
      "step": 726
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.0001495395789567932,
      "loss": 0.4234,
      "step": 727
    },
    {
      "epoch": 5.18,
      "learning_rate": 0.0001494137667597006,
      "loss": 0.4192,
      "step": 728
    },
    {
      "epoch": 5.18,
      "learning_rate": 0.00014928785099399433,
      "loss": 0.4199,
      "step": 729
    },
    {
      "epoch": 5.19,
      "learning_rate": 0.00014916183192358718,
      "loss": 0.4263,
      "step": 730
    },
    {
      "epoch": 5.19,
      "learning_rate": 0.00014903570981260832,
      "loss": 0.4266,
      "step": 731
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.000148909484925403,
      "loss": 0.4282,
      "step": 732
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.00014878315752653185,
      "loss": 0.429,
      "step": 733
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.00014865672788077027,
      "loss": 0.4195,
      "step": 734
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.00014853019625310813,
      "loss": 0.4295,
      "step": 735
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.00014840356290874888,
      "loss": 0.4232,
      "step": 736
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.00014827682811310928,
      "loss": 0.4287,
      "step": 737
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.00014814999213181866,
      "loss": 0.4249,
      "step": 738
    },
    {
      "epoch": 5.23,
      "learning_rate": 0.00014802305523071852,
      "loss": 0.425,
      "step": 739
    },
    {
      "epoch": 5.23,
      "learning_rate": 0.00014789601767586173,
      "loss": 0.4169,
      "step": 740
    },
    {
      "epoch": 5.24,
      "learning_rate": 0.0001477688797335123,
      "loss": 0.4206,
      "step": 741
    },
    {
      "epoch": 5.24,
      "learning_rate": 0.00014764164167014451,
      "loss": 0.4189,
      "step": 742
    },
    {
      "epoch": 5.25,
      "learning_rate": 0.00014751430375244256,
      "loss": 0.4256,
      "step": 743
    },
    {
      "epoch": 5.25,
      "learning_rate": 0.00014738686624729986,
      "loss": 0.4245,
      "step": 744
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.00014725932942181872,
      "loss": 0.4244,
      "step": 745
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.0001471316935433094,
      "loss": 0.4208,
      "step": 746
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.00014700395887928995,
      "loss": 0.4229,
      "step": 747
    },
    {
      "epoch": 5.27,
      "learning_rate": 0.00014687612569748535,
      "loss": 0.4257,
      "step": 748
    },
    {
      "epoch": 5.27,
      "learning_rate": 0.00014674819426582712,
      "loss": 0.4261,
      "step": 749
    },
    {
      "epoch": 5.28,
      "learning_rate": 0.00014662016485245274,
      "loss": 0.4214,
      "step": 750
    },
    {
      "epoch": 5.28,
      "learning_rate": 0.000146492037725705,
      "loss": 0.4241,
      "step": 751
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.0001463638131541315,
      "loss": 0.4305,
      "step": 752
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.00014623549140648412,
      "loss": 0.4208,
      "step": 753
    },
    {
      "epoch": 5.3,
      "learning_rate": 0.0001461070727517183,
      "loss": 0.4258,
      "step": 754
    },
    {
      "epoch": 5.3,
      "learning_rate": 0.00014597855745899274,
      "loss": 0.4193,
      "step": 755
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.00014584994579766865,
      "loss": 0.4285,
      "step": 756
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.0001457212380373091,
      "loss": 0.4204,
      "step": 757
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.00014559243444767878,
      "loss": 0.423,
      "step": 758
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.0001454635352987431,
      "loss": 0.4253,
      "step": 759
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.00014533454086066772,
      "loss": 0.4238,
      "step": 760
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.00014520545140381816,
      "loss": 0.419,
      "step": 761
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.00014507626719875897,
      "loss": 0.4245,
      "step": 762
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.0001449469885162534,
      "loss": 0.4204,
      "step": 763
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.00014481761562726262,
      "loss": 0.4262,
      "step": 764
    },
    {
      "epoch": 5.35,
      "learning_rate": 0.0001446881488029453,
      "loss": 0.4267,
      "step": 765
    },
    {
      "epoch": 5.35,
      "learning_rate": 0.00014455858831465695,
      "loss": 0.4235,
      "step": 766
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.00014442893443394945,
      "loss": 0.4197,
      "step": 767
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.00014429918743257044,
      "loss": 0.4216,
      "step": 768
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.0001441693475824626,
      "loss": 0.4222,
      "step": 769
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.00014403941515576344,
      "loss": 0.4184,
      "step": 770
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.00014390939042480428,
      "loss": 0.4194,
      "step": 771
    },
    {
      "epoch": 5.38,
      "learning_rate": 0.0001437792736621101,
      "loss": 0.4213,
      "step": 772
    },
    {
      "epoch": 5.38,
      "learning_rate": 0.0001436490651403986,
      "loss": 0.4188,
      "step": 773
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.00014351876513257986,
      "loss": 0.4192,
      "step": 774
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.00014338837391175582,
      "loss": 0.4215,
      "step": 775
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.00014325789175121946,
      "loss": 0.4198,
      "step": 776
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.00014312731892445442,
      "loss": 0.4232,
      "step": 777
    },
    {
      "epoch": 5.41,
      "learning_rate": 0.00014299665570513437,
      "loss": 0.4246,
      "step": 778
    },
    {
      "epoch": 5.41,
      "learning_rate": 0.00014286590236712237,
      "loss": 0.4185,
      "step": 779
    },
    {
      "epoch": 5.42,
      "learning_rate": 0.00014273505918447054,
      "loss": 0.4214,
      "step": 780
    },
    {
      "epoch": 5.42,
      "learning_rate": 0.0001426041264314191,
      "loss": 0.418,
      "step": 781
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.0001424731043823962,
      "loss": 0.4235,
      "step": 782
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.00014234199331201696,
      "loss": 0.424,
      "step": 783
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.0001422107934950832,
      "loss": 0.4219,
      "step": 784
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.00014207950520658274,
      "loss": 0.4266,
      "step": 785
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.0001419481287216888,
      "loss": 0.4193,
      "step": 786
    },
    {
      "epoch": 5.45,
      "learning_rate": 0.00014181666431575945,
      "loss": 0.4168,
      "step": 787
    },
    {
      "epoch": 5.45,
      "learning_rate": 0.0001416851122643371,
      "loss": 0.4196,
      "step": 788
    },
    {
      "epoch": 5.46,
      "learning_rate": 0.0001415534728431478,
      "loss": 0.4196,
      "step": 789
    },
    {
      "epoch": 5.46,
      "learning_rate": 0.00014142174632810072,
      "loss": 0.4205,
      "step": 790
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.00014128993299528762,
      "loss": 0.4248,
      "step": 791
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.0001411580331209822,
      "loss": 0.4161,
      "step": 792
    },
    {
      "epoch": 5.48,
      "learning_rate": 0.00014102604698163951,
      "loss": 0.4191,
      "step": 793
    },
    {
      "epoch": 5.48,
      "learning_rate": 0.00014089397485389548,
      "loss": 0.4233,
      "step": 794
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.00014076181701456623,
      "loss": 0.4188,
      "step": 795
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.00014062957374064752,
      "loss": 0.4274,
      "step": 796
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.00014049724530931416,
      "loss": 0.4202,
      "step": 797
    },
    {
      "epoch": 5.5,
      "learning_rate": 0.00014036483199791948,
      "loss": 0.4164,
      "step": 798
    },
    {
      "epoch": 5.5,
      "learning_rate": 0.00014023233408399472,
      "loss": 0.4226,
      "step": 799
    },
    {
      "epoch": 5.51,
      "learning_rate": 0.0001400997518452484,
      "loss": 0.4134,
      "step": 800
    },
    {
      "epoch": 5.51,
      "learning_rate": 0.00013996708555956582,
      "loss": 0.4217,
      "step": 801
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.0001398343355050084,
      "loss": 0.4215,
      "step": 802
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.00013970150195981323,
      "loss": 0.4138,
      "step": 803
    },
    {
      "epoch": 5.53,
      "learning_rate": 0.00013956858520239223,
      "loss": 0.4121,
      "step": 804
    },
    {
      "epoch": 5.53,
      "learning_rate": 0.00013943558551133186,
      "loss": 0.416,
      "step": 805
    },
    {
      "epoch": 5.54,
      "learning_rate": 0.00013930250316539238,
      "loss": 0.4203,
      "step": 806
    },
    {
      "epoch": 5.54,
      "learning_rate": 0.0001391693384435072,
      "loss": 0.4236,
      "step": 807
    },
    {
      "epoch": 5.54,
      "learning_rate": 0.0001390360916247826,
      "loss": 0.4179,
      "step": 808
    },
    {
      "epoch": 5.55,
      "learning_rate": 0.0001389027629884966,
      "loss": 0.4136,
      "step": 809
    },
    {
      "epoch": 5.55,
      "learning_rate": 0.00013876935281409907,
      "loss": 0.4257,
      "step": 810
    },
    {
      "epoch": 5.56,
      "learning_rate": 0.0001386358613812105,
      "loss": 0.4234,
      "step": 811
    },
    {
      "epoch": 5.56,
      "learning_rate": 0.0001385022889696218,
      "loss": 0.4177,
      "step": 812
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.00013836863585929365,
      "loss": 0.4185,
      "step": 813
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.0001382349023303558,
      "loss": 0.4192,
      "step": 814
    },
    {
      "epoch": 5.58,
      "learning_rate": 0.0001381010886631066,
      "loss": 0.4187,
      "step": 815
    },
    {
      "epoch": 5.58,
      "learning_rate": 0.00013796719513801232,
      "loss": 0.4197,
      "step": 816
    },
    {
      "epoch": 5.59,
      "learning_rate": 0.0001378332220357066,
      "loss": 0.4184,
      "step": 817
    },
    {
      "epoch": 5.59,
      "learning_rate": 0.00013769916963698997,
      "loss": 0.4203,
      "step": 818
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.000137565038222829,
      "loss": 0.4198,
      "step": 819
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.00013743082807435615,
      "loss": 0.4211,
      "step": 820
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.00013729653947286847,
      "loss": 0.4132,
      "step": 821
    },
    {
      "epoch": 5.61,
      "learning_rate": 0.00013716217269982788,
      "loss": 0.4168,
      "step": 822
    },
    {
      "epoch": 5.61,
      "learning_rate": 0.00013702772803685984,
      "loss": 0.417,
      "step": 823
    },
    {
      "epoch": 5.62,
      "learning_rate": 0.00013689320576575322,
      "loss": 0.4247,
      "step": 824
    },
    {
      "epoch": 5.62,
      "learning_rate": 0.00013675860616845954,
      "loss": 0.4186,
      "step": 825
    },
    {
      "epoch": 5.63,
      "learning_rate": 0.00013662392952709228,
      "loss": 0.4116,
      "step": 826
    },
    {
      "epoch": 5.63,
      "learning_rate": 0.0001364891761239266,
      "loss": 0.4087,
      "step": 827
    },
    {
      "epoch": 5.63,
      "eval_loss": 0.4685542583465576,
      "eval_runtime": 28.2711,
      "eval_samples_per_second": 7.074,
      "eval_steps_per_second": 0.884,
      "step": 827
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00013635434624139828,
      "loss": 0.4133,
      "step": 828
    },
    {
      "epoch": 6.01,
      "learning_rate": 0.00013621944016210366,
      "loss": 0.4181,
      "step": 829
    },
    {
      "epoch": 6.01,
      "learning_rate": 0.00013608445816879866,
      "loss": 0.414,
      "step": 830
    },
    {
      "epoch": 6.02,
      "learning_rate": 0.00013594940054439825,
      "loss": 0.4165,
      "step": 831
    },
    {
      "epoch": 6.02,
      "learning_rate": 0.00013581426757197605,
      "loss": 0.4153,
      "step": 832
    },
    {
      "epoch": 6.03,
      "learning_rate": 0.00013567905953476355,
      "loss": 0.4218,
      "step": 833
    },
    {
      "epoch": 6.03,
      "learning_rate": 0.00013554377671614958,
      "loss": 0.4177,
      "step": 834
    },
    {
      "epoch": 6.04,
      "learning_rate": 0.00013540841939967962,
      "loss": 0.4198,
      "step": 835
    },
    {
      "epoch": 6.04,
      "learning_rate": 0.00013527298786905544,
      "loss": 0.4194,
      "step": 836
    },
    {
      "epoch": 6.04,
      "learning_rate": 0.0001351374824081343,
      "loss": 0.4157,
      "step": 837
    },
    {
      "epoch": 6.05,
      "learning_rate": 0.0001350019033009283,
      "loss": 0.4109,
      "step": 838
    },
    {
      "epoch": 6.05,
      "learning_rate": 0.00013486625083160414,
      "loss": 0.4195,
      "step": 839
    },
    {
      "epoch": 6.06,
      "learning_rate": 0.00013473052528448201,
      "loss": 0.416,
      "step": 840
    },
    {
      "epoch": 6.06,
      "learning_rate": 0.00013459472694403552,
      "loss": 0.4198,
      "step": 841
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.00013445885609489068,
      "loss": 0.4155,
      "step": 842
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.0001343229130218255,
      "loss": 0.4221,
      "step": 843
    },
    {
      "epoch": 6.08,
      "learning_rate": 0.00013418689800976942,
      "loss": 0.419,
      "step": 844
    },
    {
      "epoch": 6.08,
      "learning_rate": 0.00013405081134380264,
      "loss": 0.4186,
      "step": 845
    },
    {
      "epoch": 6.09,
      "learning_rate": 0.00013391465330915556,
      "loss": 0.4148,
      "step": 846
    },
    {
      "epoch": 6.09,
      "learning_rate": 0.00013377842419120807,
      "loss": 0.4227,
      "step": 847
    },
    {
      "epoch": 6.1,
      "learning_rate": 0.00013364212427548916,
      "loss": 0.4155,
      "step": 848
    },
    {
      "epoch": 6.1,
      "learning_rate": 0.0001335057538476762,
      "loss": 0.4139,
      "step": 849
    },
    {
      "epoch": 6.1,
      "learning_rate": 0.00013336931319359426,
      "loss": 0.4136,
      "step": 850
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.00013323280259921574,
      "loss": 0.4168,
      "step": 851
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.00013309622235065942,
      "loss": 0.4132,
      "step": 852
    },
    {
      "epoch": 6.12,
      "learning_rate": 0.0001329595727341903,
      "loss": 0.4124,
      "step": 853
    },
    {
      "epoch": 6.12,
      "learning_rate": 0.00013282285403621864,
      "loss": 0.414,
      "step": 854
    },
    {
      "epoch": 6.13,
      "learning_rate": 0.0001326860665432995,
      "loss": 0.4164,
      "step": 855
    },
    {
      "epoch": 6.13,
      "learning_rate": 0.00013254921054213224,
      "loss": 0.41,
      "step": 856
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.00013241228631955963,
      "loss": 0.41,
      "step": 857
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.00013227529416256754,
      "loss": 0.4124,
      "step": 858
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.0001321382343582842,
      "loss": 0.4134,
      "step": 859
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.00013200110719397968,
      "loss": 0.4162,
      "step": 860
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.00013186391295706517,
      "loss": 0.4216,
      "step": 861
    },
    {
      "epoch": 6.16,
      "learning_rate": 0.00013172665193509242,
      "loss": 0.412,
      "step": 862
    },
    {
      "epoch": 6.16,
      "learning_rate": 0.00013158932441575326,
      "loss": 0.4089,
      "step": 863
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.00013145193068687876,
      "loss": 0.4132,
      "step": 864
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.00013131447103643885,
      "loss": 0.4075,
      "step": 865
    },
    {
      "epoch": 6.18,
      "learning_rate": 0.00013117694575254162,
      "loss": 0.4165,
      "step": 866
    },
    {
      "epoch": 6.18,
      "learning_rate": 0.00013103935512343273,
      "loss": 0.4139,
      "step": 867
    },
    {
      "epoch": 6.19,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.4095,
      "step": 868
    },
    {
      "epoch": 6.19,
      "learning_rate": 0.00013076397898324665,
      "loss": 0.416,
      "step": 869
    },
    {
      "epoch": 6.2,
      "learning_rate": 0.00013062619404934317,
      "loss": 0.4207,
      "step": 870
    },
    {
      "epoch": 6.2,
      "learning_rate": 0.00013048834492457415,
      "loss": 0.4042,
      "step": 871
    },
    {
      "epoch": 6.21,
      "learning_rate": 0.00013035043189786393,
      "loss": 0.4194,
      "step": 872
    },
    {
      "epoch": 6.21,
      "learning_rate": 0.00013021245525827096,
      "loss": 0.4159,
      "step": 873
    },
    {
      "epoch": 6.21,
      "learning_rate": 0.00013007441529498673,
      "loss": 0.4138,
      "step": 874
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.00012993631229733582,
      "loss": 0.4129,
      "step": 875
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.0001297981465547746,
      "loss": 0.4063,
      "step": 876
    },
    {
      "epoch": 6.23,
      "learning_rate": 0.0001296599183568911,
      "loss": 0.4112,
      "step": 877
    },
    {
      "epoch": 6.23,
      "learning_rate": 0.00012952162799340425,
      "loss": 0.4066,
      "step": 878
    },
    {
      "epoch": 6.24,
      "learning_rate": 0.00012938327575416327,
      "loss": 0.4118,
      "step": 879
    },
    {
      "epoch": 6.24,
      "learning_rate": 0.00012924486192914705,
      "loss": 0.4091,
      "step": 880
    },
    {
      "epoch": 6.25,
      "learning_rate": 0.00012910638680846358,
      "loss": 0.4155,
      "step": 881
    },
    {
      "epoch": 6.25,
      "learning_rate": 0.00012896785068234926,
      "loss": 0.4133,
      "step": 882
    },
    {
      "epoch": 6.26,
      "learning_rate": 0.00012882925384116842,
      "loss": 0.4117,
      "step": 883
    },
    {
      "epoch": 6.26,
      "learning_rate": 0.0001286905965754127,
      "loss": 0.4142,
      "step": 884
    },
    {
      "epoch": 6.27,
      "learning_rate": 0.0001285518791757002,
      "loss": 0.409,
      "step": 885
    },
    {
      "epoch": 6.27,
      "learning_rate": 0.00012841310193277528,
      "loss": 0.409,
      "step": 886
    },
    {
      "epoch": 6.27,
      "learning_rate": 0.0001282742651375076,
      "loss": 0.4124,
      "step": 887
    },
    {
      "epoch": 6.28,
      "learning_rate": 0.00012813536908089164,
      "loss": 0.4135,
      "step": 888
    },
    {
      "epoch": 6.28,
      "learning_rate": 0.0001279964140540461,
      "loss": 0.4045,
      "step": 889
    },
    {
      "epoch": 6.29,
      "learning_rate": 0.00012785740034821329,
      "loss": 0.4134,
      "step": 890
    },
    {
      "epoch": 6.29,
      "learning_rate": 0.00012771832825475852,
      "loss": 0.4157,
      "step": 891
    },
    {
      "epoch": 6.3,
      "learning_rate": 0.0001275791980651695,
      "loss": 0.4143,
      "step": 892
    },
    {
      "epoch": 6.3,
      "learning_rate": 0.0001274400100710556,
      "loss": 0.4146,
      "step": 893
    },
    {
      "epoch": 6.31,
      "learning_rate": 0.00012730076456414746,
      "loss": 0.411,
      "step": 894
    },
    {
      "epoch": 6.31,
      "learning_rate": 0.0001271614618362962,
      "loss": 0.4131,
      "step": 895
    },
    {
      "epoch": 6.32,
      "learning_rate": 0.00012702210217947288,
      "loss": 0.4162,
      "step": 896
    },
    {
      "epoch": 6.32,
      "learning_rate": 0.0001268826858857679,
      "loss": 0.4099,
      "step": 897
    },
    {
      "epoch": 6.32,
      "learning_rate": 0.00012674321324739038,
      "loss": 0.4135,
      "step": 898
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.00012660368455666752,
      "loss": 0.4106,
      "step": 899
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.00012646410010604397,
      "loss": 0.4027,
      "step": 900
    },
    {
      "epoch": 6.34,
      "learning_rate": 0.00012632446018808128,
      "loss": 0.4118,
      "step": 901
    },
    {
      "epoch": 6.34,
      "learning_rate": 0.00012618476509545725,
      "loss": 0.4143,
      "step": 902
    },
    {
      "epoch": 6.35,
      "learning_rate": 0.00012604501512096533,
      "loss": 0.414,
      "step": 903
    },
    {
      "epoch": 6.35,
      "learning_rate": 0.000125905210557514,
      "loss": 0.4064,
      "step": 904
    },
    {
      "epoch": 6.36,
      "learning_rate": 0.00012576535169812615,
      "loss": 0.4188,
      "step": 905
    },
    {
      "epoch": 6.36,
      "learning_rate": 0.00012562543883593848,
      "loss": 0.4048,
      "step": 906
    },
    {
      "epoch": 6.37,
      "learning_rate": 0.00012548547226420089,
      "loss": 0.4094,
      "step": 907
    },
    {
      "epoch": 6.37,
      "learning_rate": 0.0001253454522762758,
      "loss": 0.4055,
      "step": 908
    },
    {
      "epoch": 6.38,
      "learning_rate": 0.00012520537916563756,
      "loss": 0.4097,
      "step": 909
    },
    {
      "epoch": 6.38,
      "learning_rate": 0.00012506525322587207,
      "loss": 0.4064,
      "step": 910
    },
    {
      "epoch": 6.38,
      "learning_rate": 0.0001249250747506757,
      "loss": 0.4076,
      "step": 911
    },
    {
      "epoch": 6.39,
      "learning_rate": 0.00012478484403385506,
      "loss": 0.4081,
      "step": 912
    },
    {
      "epoch": 6.39,
      "learning_rate": 0.00012464456136932625,
      "loss": 0.4122,
      "step": 913
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.0001245042270511142,
      "loss": 0.4073,
      "step": 914
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.0001243638413733522,
      "loss": 0.4098,
      "step": 915
    },
    {
      "epoch": 6.41,
      "learning_rate": 0.00012422340463028107,
      "loss": 0.413,
      "step": 916
    },
    {
      "epoch": 6.41,
      "learning_rate": 0.00012408291711624877,
      "loss": 0.4101,
      "step": 917
    },
    {
      "epoch": 6.42,
      "learning_rate": 0.00012394237912570957,
      "loss": 0.4128,
      "step": 918
    },
    {
      "epoch": 6.42,
      "learning_rate": 0.00012380179095322364,
      "loss": 0.4062,
      "step": 919
    },
    {
      "epoch": 6.43,
      "learning_rate": 0.0001236611528934562,
      "loss": 0.4119,
      "step": 920
    },
    {
      "epoch": 6.43,
      "learning_rate": 0.00012352046524117716,
      "loss": 0.4093,
      "step": 921
    },
    {
      "epoch": 6.44,
      "learning_rate": 0.0001233797282912603,
      "loss": 0.4072,
      "step": 922
    },
    {
      "epoch": 6.44,
      "learning_rate": 0.00012323894233868274,
      "loss": 0.4048,
      "step": 923
    },
    {
      "epoch": 6.44,
      "learning_rate": 0.00012309810767852433,
      "loss": 0.4117,
      "step": 924
    },
    {
      "epoch": 6.45,
      "learning_rate": 0.00012295722460596697,
      "loss": 0.4123,
      "step": 925
    },
    {
      "epoch": 6.45,
      "learning_rate": 0.0001228162934162941,
      "loss": 0.4127,
      "step": 926
    },
    {
      "epoch": 6.46,
      "learning_rate": 0.00012267531440488986,
      "loss": 0.4106,
      "step": 927
    },
    {
      "epoch": 6.46,
      "learning_rate": 0.00012253428786723877,
      "loss": 0.4078,
      "step": 928
    },
    {
      "epoch": 6.47,
      "learning_rate": 0.00012239321409892494,
      "loss": 0.4111,
      "step": 929
    },
    {
      "epoch": 6.47,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.4123,
      "step": 930
    },
    {
      "epoch": 6.48,
      "learning_rate": 0.00012211092605313972,
      "loss": 0.4049,
      "step": 931
    },
    {
      "epoch": 6.48,
      "learning_rate": 0.00012196971236732894,
      "loss": 0.406,
      "step": 932
    },
    {
      "epoch": 6.49,
      "learning_rate": 0.00012182845263417549,
      "loss": 0.4085,
      "step": 933
    },
    {
      "epoch": 6.49,
      "learning_rate": 0.00012168714714975218,
      "loss": 0.407,
      "step": 934
    },
    {
      "epoch": 6.49,
      "learning_rate": 0.00012154579621022777,
      "loss": 0.413,
      "step": 935
    },
    {
      "epoch": 6.5,
      "learning_rate": 0.0001214044001118663,
      "loss": 0.3998,
      "step": 936
    },
    {
      "epoch": 6.5,
      "learning_rate": 0.00012126295915102639,
      "loss": 0.4042,
      "step": 937
    },
    {
      "epoch": 6.51,
      "learning_rate": 0.00012112147362416076,
      "loss": 0.4118,
      "step": 938
    },
    {
      "epoch": 6.51,
      "learning_rate": 0.00012097994382781547,
      "loss": 0.4091,
      "step": 939
    },
    {
      "epoch": 6.52,
      "learning_rate": 0.00012083837005862946,
      "loss": 0.4009,
      "step": 940
    },
    {
      "epoch": 6.52,
      "learning_rate": 0.00012069675261333375,
      "loss": 0.4124,
      "step": 941
    },
    {
      "epoch": 6.53,
      "learning_rate": 0.00012055509178875097,
      "loss": 0.4041,
      "step": 942
    },
    {
      "epoch": 6.53,
      "learning_rate": 0.0001204133878817946,
      "loss": 0.4029,
      "step": 943
    },
    {
      "epoch": 6.54,
      "learning_rate": 0.00012027164118946844,
      "loss": 0.4104,
      "step": 944
    },
    {
      "epoch": 6.54,
      "learning_rate": 0.00012012985200886602,
      "loss": 0.4065,
      "step": 945
    },
    {
      "epoch": 6.55,
      "learning_rate": 0.00011998802063716987,
      "loss": 0.4074,
      "step": 946
    },
    {
      "epoch": 6.55,
      "learning_rate": 0.00011984614737165094,
      "loss": 0.4077,
      "step": 947
    },
    {
      "epoch": 6.55,
      "learning_rate": 0.00011970423250966807,
      "loss": 0.4136,
      "step": 948
    },
    {
      "epoch": 6.56,
      "learning_rate": 0.00011956227634866714,
      "loss": 0.4124,
      "step": 949
    },
    {
      "epoch": 6.56,
      "learning_rate": 0.00011942027918618074,
      "loss": 0.4058,
      "step": 950
    },
    {
      "epoch": 6.57,
      "learning_rate": 0.00011927824131982734,
      "loss": 0.4066,
      "step": 951
    },
    {
      "epoch": 6.57,
      "learning_rate": 0.00011913616304731063,
      "loss": 0.4091,
      "step": 952
    },
    {
      "epoch": 6.58,
      "learning_rate": 0.0001189940446664192,
      "loss": 0.41,
      "step": 953
    },
    {
      "epoch": 6.58,
      "learning_rate": 0.00011885188647502546,
      "loss": 0.3986,
      "step": 954
    },
    {
      "epoch": 6.59,
      "learning_rate": 0.00011870968877108546,
      "loss": 0.4116,
      "step": 955
    },
    {
      "epoch": 6.59,
      "learning_rate": 0.00011856745185263791,
      "loss": 0.4157,
      "step": 956
    },
    {
      "epoch": 6.6,
      "learning_rate": 0.00011842517601780388,
      "loss": 0.407,
      "step": 957
    },
    {
      "epoch": 6.6,
      "learning_rate": 0.00011828286156478585,
      "loss": 0.4098,
      "step": 958
    },
    {
      "epoch": 6.61,
      "learning_rate": 0.00011814050879186731,
      "loss": 0.4045,
      "step": 959
    },
    {
      "epoch": 6.61,
      "learning_rate": 0.0001179981179974121,
      "loss": 0.4067,
      "step": 960
    },
    {
      "epoch": 6.61,
      "learning_rate": 0.00011785568947986367,
      "loss": 0.4101,
      "step": 961
    },
    {
      "epoch": 6.62,
      "learning_rate": 0.0001177132235377446,
      "loss": 0.4046,
      "step": 962
    },
    {
      "epoch": 6.62,
      "learning_rate": 0.00011757072046965589,
      "loss": 0.4024,
      "step": 963
    },
    {
      "epoch": 6.63,
      "learning_rate": 0.00011742818057427636,
      "loss": 0.3982,
      "step": 964
    },
    {
      "epoch": 6.63,
      "learning_rate": 0.00011728560415036201,
      "loss": 0.399,
      "step": 965
    },
    {
      "epoch": 6.63,
      "eval_loss": 0.47236838936805725,
      "eval_runtime": 28.2487,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.885,
      "step": 965
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00011714299149674537,
      "loss": 0.402,
      "step": 966
    },
    {
      "epoch": 7.01,
      "learning_rate": 0.00011700034291233499,
      "loss": 0.4055,
      "step": 967
    },
    {
      "epoch": 7.01,
      "learning_rate": 0.00011685765869611463,
      "loss": 0.4065,
      "step": 968
    },
    {
      "epoch": 7.02,
      "learning_rate": 0.00011671493914714279,
      "loss": 0.4112,
      "step": 969
    },
    {
      "epoch": 7.02,
      "learning_rate": 0.00011657218456455206,
      "loss": 0.4032,
      "step": 970
    },
    {
      "epoch": 7.03,
      "learning_rate": 0.00011642939524754832,
      "loss": 0.404,
      "step": 971
    },
    {
      "epoch": 7.03,
      "learning_rate": 0.00011628657149541045,
      "loss": 0.402,
      "step": 972
    },
    {
      "epoch": 7.04,
      "learning_rate": 0.00011614371360748935,
      "loss": 0.407,
      "step": 973
    },
    {
      "epoch": 7.04,
      "learning_rate": 0.00011600082188320752,
      "loss": 0.4095,
      "step": 974
    },
    {
      "epoch": 7.05,
      "learning_rate": 0.00011585789662205835,
      "loss": 0.4102,
      "step": 975
    },
    {
      "epoch": 7.05,
      "learning_rate": 0.00011571493812360561,
      "loss": 0.407,
      "step": 976
    },
    {
      "epoch": 7.05,
      "learning_rate": 0.00011557194668748262,
      "loss": 0.4038,
      "step": 977
    },
    {
      "epoch": 7.06,
      "learning_rate": 0.00011542892261339178,
      "loss": 0.4073,
      "step": 978
    },
    {
      "epoch": 7.06,
      "learning_rate": 0.00011528586620110396,
      "loss": 0.3989,
      "step": 979
    },
    {
      "epoch": 7.07,
      "learning_rate": 0.00011514277775045768,
      "loss": 0.4077,
      "step": 980
    },
    {
      "epoch": 7.07,
      "learning_rate": 0.00011499965756135873,
      "loss": 0.404,
      "step": 981
    },
    {
      "epoch": 7.08,
      "learning_rate": 0.0001148565059337794,
      "loss": 0.4096,
      "step": 982
    },
    {
      "epoch": 7.08,
      "learning_rate": 0.00011471332316775773,
      "loss": 0.4091,
      "step": 983
    },
    {
      "epoch": 7.09,
      "learning_rate": 0.0001145701095633973,
      "loss": 0.4082,
      "step": 984
    },
    {
      "epoch": 7.09,
      "learning_rate": 0.00011442686542086609,
      "loss": 0.4112,
      "step": 985
    },
    {
      "epoch": 7.1,
      "learning_rate": 0.00011428359104039617,
      "loss": 0.404,
      "step": 986
    },
    {
      "epoch": 7.1,
      "learning_rate": 0.00011414028672228293,
      "loss": 0.4059,
      "step": 987
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.00011399695276688469,
      "loss": 0.3987,
      "step": 988
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.00011385358947462166,
      "loss": 0.4035,
      "step": 989
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.00011371019714597562,
      "loss": 0.4009,
      "step": 990
    },
    {
      "epoch": 7.12,
      "learning_rate": 0.00011356677608148933,
      "loss": 0.4082,
      "step": 991
    },
    {
      "epoch": 7.12,
      "learning_rate": 0.00011342332658176555,
      "loss": 0.4025,
      "step": 992
    },
    {
      "epoch": 7.13,
      "learning_rate": 0.00011327984894746686,
      "loss": 0.4076,
      "step": 993
    },
    {
      "epoch": 7.13,
      "learning_rate": 0.00011313634347931466,
      "loss": 0.4026,
      "step": 994
    },
    {
      "epoch": 7.14,
      "learning_rate": 0.00011299281047808877,
      "loss": 0.4028,
      "step": 995
    },
    {
      "epoch": 7.14,
      "learning_rate": 0.00011284925024462665,
      "loss": 0.4021,
      "step": 996
    },
    {
      "epoch": 7.15,
      "learning_rate": 0.00011270566307982291,
      "loss": 0.4026,
      "step": 997
    },
    {
      "epoch": 7.15,
      "learning_rate": 0.00011256204928462857,
      "loss": 0.3941,
      "step": 998
    },
    {
      "epoch": 7.16,
      "learning_rate": 0.00011241840916005043,
      "loss": 0.4095,
      "step": 999
    },
    {
      "epoch": 7.16,
      "learning_rate": 0.00011227474300715055,
      "loss": 0.4073,
      "step": 1000
    },
    {
      "epoch": 7.16,
      "learning_rate": 0.0001121310511270455,
      "loss": 0.3998,
      "step": 1001
    },
    {
      "epoch": 7.17,
      "learning_rate": 0.00011198733382090576,
      "loss": 0.3974,
      "step": 1002
    },
    {
      "epoch": 7.17,
      "learning_rate": 0.00011184359138995517,
      "loss": 0.4039,
      "step": 1003
    },
    {
      "epoch": 7.18,
      "learning_rate": 0.00011169982413547012,
      "loss": 0.401,
      "step": 1004
    },
    {
      "epoch": 7.18,
      "learning_rate": 0.00011155603235877912,
      "loss": 0.3985,
      "step": 1005
    },
    {
      "epoch": 7.19,
      "learning_rate": 0.00011141221636126202,
      "loss": 0.3997,
      "step": 1006
    },
    {
      "epoch": 7.19,
      "learning_rate": 0.00011126837644434953,
      "loss": 0.4027,
      "step": 1007
    },
    {
      "epoch": 7.2,
      "learning_rate": 0.00011112451290952237,
      "loss": 0.4002,
      "step": 1008
    },
    {
      "epoch": 7.2,
      "learning_rate": 0.00011098062605831084,
      "loss": 0.4048,
      "step": 1009
    },
    {
      "epoch": 7.21,
      "learning_rate": 0.00011083671619229408,
      "loss": 0.4022,
      "step": 1010
    },
    {
      "epoch": 7.21,
      "learning_rate": 0.00011069278361309945,
      "loss": 0.3989,
      "step": 1011
    },
    {
      "epoch": 7.22,
      "learning_rate": 0.00011054882862240199,
      "loss": 0.4082,
      "step": 1012
    },
    {
      "epoch": 7.22,
      "learning_rate": 0.00011040485152192363,
      "loss": 0.3989,
      "step": 1013
    },
    {
      "epoch": 7.22,
      "learning_rate": 0.00011026085261343271,
      "loss": 0.4064,
      "step": 1014
    },
    {
      "epoch": 7.23,
      "learning_rate": 0.00011011683219874323,
      "loss": 0.3947,
      "step": 1015
    },
    {
      "epoch": 7.23,
      "learning_rate": 0.00010997279057971425,
      "loss": 0.3972,
      "step": 1016
    },
    {
      "epoch": 7.24,
      "learning_rate": 0.00010982872805824936,
      "loss": 0.4013,
      "step": 1017
    },
    {
      "epoch": 7.24,
      "learning_rate": 0.00010968464493629584,
      "loss": 0.3996,
      "step": 1018
    },
    {
      "epoch": 7.25,
      "learning_rate": 0.00010954054151584425,
      "loss": 0.404,
      "step": 1019
    },
    {
      "epoch": 7.25,
      "learning_rate": 0.00010939641809892767,
      "loss": 0.4021,
      "step": 1020
    },
    {
      "epoch": 7.26,
      "learning_rate": 0.00010925227498762106,
      "loss": 0.402,
      "step": 1021
    },
    {
      "epoch": 7.26,
      "learning_rate": 0.00010910811248404065,
      "loss": 0.398,
      "step": 1022
    },
    {
      "epoch": 7.27,
      "learning_rate": 0.00010896393089034336,
      "loss": 0.4011,
      "step": 1023
    },
    {
      "epoch": 7.27,
      "learning_rate": 0.00010881973050872612,
      "loss": 0.4004,
      "step": 1024
    },
    {
      "epoch": 7.27,
      "learning_rate": 0.0001086755116414252,
      "loss": 0.3949,
      "step": 1025
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.00010853127459071567,
      "loss": 0.4068,
      "step": 1026
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.00010838701965891063,
      "loss": 0.4015,
      "step": 1027
    },
    {
      "epoch": 7.29,
      "learning_rate": 0.00010824274714836073,
      "loss": 0.3982,
      "step": 1028
    },
    {
      "epoch": 7.29,
      "learning_rate": 0.00010809845736145346,
      "loss": 0.401,
      "step": 1029
    },
    {
      "epoch": 7.3,
      "learning_rate": 0.00010795415060061243,
      "loss": 0.4076,
      "step": 1030
    },
    {
      "epoch": 7.3,
      "learning_rate": 0.00010780982716829698,
      "loss": 0.4029,
      "step": 1031
    },
    {
      "epoch": 7.31,
      "learning_rate": 0.00010766548736700124,
      "loss": 0.3954,
      "step": 1032
    },
    {
      "epoch": 7.31,
      "learning_rate": 0.00010752113149925378,
      "loss": 0.4047,
      "step": 1033
    },
    {
      "epoch": 7.32,
      "learning_rate": 0.00010737675986761677,
      "loss": 0.3969,
      "step": 1034
    },
    {
      "epoch": 7.32,
      "learning_rate": 0.00010723237277468538,
      "loss": 0.4052,
      "step": 1035
    },
    {
      "epoch": 7.33,
      "learning_rate": 0.0001070879705230873,
      "loss": 0.4001,
      "step": 1036
    },
    {
      "epoch": 7.33,
      "learning_rate": 0.00010694355341548188,
      "loss": 0.4037,
      "step": 1037
    },
    {
      "epoch": 7.33,
      "learning_rate": 0.0001067991217545597,
      "loss": 0.3952,
      "step": 1038
    },
    {
      "epoch": 7.34,
      "learning_rate": 0.00010665467584304178,
      "loss": 0.4021,
      "step": 1039
    },
    {
      "epoch": 7.34,
      "learning_rate": 0.00010651021598367906,
      "loss": 0.3973,
      "step": 1040
    },
    {
      "epoch": 7.35,
      "learning_rate": 0.00010636574247925161,
      "loss": 0.3979,
      "step": 1041
    },
    {
      "epoch": 7.35,
      "learning_rate": 0.00010622125563256821,
      "loss": 0.4043,
      "step": 1042
    },
    {
      "epoch": 7.36,
      "learning_rate": 0.0001060767557464656,
      "loss": 0.4024,
      "step": 1043
    },
    {
      "epoch": 7.36,
      "learning_rate": 0.00010593224312380776,
      "loss": 0.398,
      "step": 1044
    },
    {
      "epoch": 7.37,
      "learning_rate": 0.00010578771806748546,
      "loss": 0.4003,
      "step": 1045
    },
    {
      "epoch": 7.37,
      "learning_rate": 0.00010564318088041551,
      "loss": 0.3953,
      "step": 1046
    },
    {
      "epoch": 7.38,
      "learning_rate": 0.0001054986318655401,
      "loss": 0.3937,
      "step": 1047
    },
    {
      "epoch": 7.38,
      "learning_rate": 0.00010535407132582622,
      "loss": 0.4051,
      "step": 1048
    },
    {
      "epoch": 7.39,
      "learning_rate": 0.00010520949956426505,
      "loss": 0.398,
      "step": 1049
    },
    {
      "epoch": 7.39,
      "learning_rate": 0.00010506491688387127,
      "loss": 0.3946,
      "step": 1050
    },
    {
      "epoch": 7.39,
      "learning_rate": 0.00010492032358768247,
      "loss": 0.3993,
      "step": 1051
    },
    {
      "epoch": 7.4,
      "learning_rate": 0.00010477571997875848,
      "loss": 0.397,
      "step": 1052
    },
    {
      "epoch": 7.4,
      "learning_rate": 0.00010463110636018065,
      "loss": 0.3992,
      "step": 1053
    },
    {
      "epoch": 7.41,
      "learning_rate": 0.00010448648303505151,
      "loss": 0.4015,
      "step": 1054
    },
    {
      "epoch": 7.41,
      "learning_rate": 0.00010434185030649372,
      "loss": 0.3984,
      "step": 1055
    },
    {
      "epoch": 7.42,
      "learning_rate": 0.0001041972084776498,
      "loss": 0.4009,
      "step": 1056
    },
    {
      "epoch": 7.42,
      "learning_rate": 0.00010405255785168131,
      "loss": 0.4009,
      "step": 1057
    },
    {
      "epoch": 7.43,
      "learning_rate": 0.00010390789873176818,
      "loss": 0.401,
      "step": 1058
    },
    {
      "epoch": 7.43,
      "learning_rate": 0.0001037632314211082,
      "loss": 0.3966,
      "step": 1059
    },
    {
      "epoch": 7.44,
      "learning_rate": 0.00010361855622291637,
      "loss": 0.3975,
      "step": 1060
    },
    {
      "epoch": 7.44,
      "learning_rate": 0.00010347387344042408,
      "loss": 0.3994,
      "step": 1061
    },
    {
      "epoch": 7.44,
      "learning_rate": 0.00010332918337687879,
      "loss": 0.3993,
      "step": 1062
    },
    {
      "epoch": 7.45,
      "learning_rate": 0.00010318448633554308,
      "loss": 0.3985,
      "step": 1063
    },
    {
      "epoch": 7.45,
      "learning_rate": 0.0001030397826196943,
      "loss": 0.3957,
      "step": 1064
    },
    {
      "epoch": 7.46,
      "learning_rate": 0.00010289507253262358,
      "loss": 0.4014,
      "step": 1065
    },
    {
      "epoch": 7.46,
      "learning_rate": 0.00010275035637763563,
      "loss": 0.3962,
      "step": 1066
    },
    {
      "epoch": 7.47,
      "learning_rate": 0.00010260563445804776,
      "loss": 0.3978,
      "step": 1067
    },
    {
      "epoch": 7.47,
      "learning_rate": 0.0001024609070771893,
      "loss": 0.3981,
      "step": 1068
    },
    {
      "epoch": 7.48,
      "learning_rate": 0.00010231617453840119,
      "loss": 0.4024,
      "step": 1069
    },
    {
      "epoch": 7.48,
      "learning_rate": 0.00010217143714503508,
      "loss": 0.3965,
      "step": 1070
    },
    {
      "epoch": 7.49,
      "learning_rate": 0.00010202669520045278,
      "loss": 0.3952,
      "step": 1071
    },
    {
      "epoch": 7.49,
      "learning_rate": 0.00010188194900802566,
      "loss": 0.401,
      "step": 1072
    },
    {
      "epoch": 7.5,
      "learning_rate": 0.00010173719887113402,
      "loss": 0.3989,
      "step": 1073
    },
    {
      "epoch": 7.5,
      "learning_rate": 0.00010159244509316644,
      "loss": 0.3986,
      "step": 1074
    },
    {
      "epoch": 7.5,
      "learning_rate": 0.00010144768797751905,
      "loss": 0.3936,
      "step": 1075
    },
    {
      "epoch": 7.51,
      "learning_rate": 0.00010130292782759507,
      "loss": 0.3933,
      "step": 1076
    },
    {
      "epoch": 7.51,
      "learning_rate": 0.00010115816494680399,
      "loss": 0.3998,
      "step": 1077
    },
    {
      "epoch": 7.52,
      "learning_rate": 0.00010101339963856111,
      "loss": 0.3937,
      "step": 1078
    },
    {
      "epoch": 7.52,
      "learning_rate": 0.00010086863220628675,
      "loss": 0.3925,
      "step": 1079
    },
    {
      "epoch": 7.53,
      "learning_rate": 0.00010072386295340572,
      "loss": 0.399,
      "step": 1080
    },
    {
      "epoch": 7.53,
      "learning_rate": 0.00010057909218334665,
      "loss": 0.4014,
      "step": 1081
    },
    {
      "epoch": 7.54,
      "learning_rate": 0.00010043432019954131,
      "loss": 0.3977,
      "step": 1082
    },
    {
      "epoch": 7.54,
      "learning_rate": 0.00010028954730542406,
      "loss": 0.401,
      "step": 1083
    },
    {
      "epoch": 7.55,
      "learning_rate": 0.0001001447738044311,
      "loss": 0.3986,
      "step": 1084
    },
    {
      "epoch": 7.55,
      "learning_rate": 0.0001,
      "loss": 0.3989,
      "step": 1085
    },
    {
      "epoch": 7.56,
      "learning_rate": 9.985522619556893e-05,
      "loss": 0.3977,
      "step": 1086
    },
    {
      "epoch": 7.56,
      "learning_rate": 9.971045269457598e-05,
      "loss": 0.3971,
      "step": 1087
    },
    {
      "epoch": 7.56,
      "learning_rate": 9.956567980045872e-05,
      "loss": 0.3948,
      "step": 1088
    },
    {
      "epoch": 7.57,
      "learning_rate": 9.942090781665336e-05,
      "loss": 0.402,
      "step": 1089
    },
    {
      "epoch": 7.57,
      "learning_rate": 9.927613704659429e-05,
      "loss": 0.3976,
      "step": 1090
    },
    {
      "epoch": 7.58,
      "learning_rate": 9.913136779371326e-05,
      "loss": 0.395,
      "step": 1091
    },
    {
      "epoch": 7.58,
      "learning_rate": 9.898660036143893e-05,
      "loss": 0.3977,
      "step": 1092
    },
    {
      "epoch": 7.59,
      "learning_rate": 9.884183505319604e-05,
      "loss": 0.3967,
      "step": 1093
    },
    {
      "epoch": 7.59,
      "learning_rate": 9.869707217240497e-05,
      "loss": 0.3939,
      "step": 1094
    },
    {
      "epoch": 7.6,
      "learning_rate": 9.855231202248097e-05,
      "loss": 0.4004,
      "step": 1095
    },
    {
      "epoch": 7.6,
      "learning_rate": 9.840755490683357e-05,
      "loss": 0.4001,
      "step": 1096
    },
    {
      "epoch": 7.61,
      "learning_rate": 9.8262801128866e-05,
      "loss": 0.3912,
      "step": 1097
    },
    {
      "epoch": 7.61,
      "learning_rate": 9.811805099197438e-05,
      "loss": 0.397,
      "step": 1098
    },
    {
      "epoch": 7.61,
      "learning_rate": 9.797330479954725e-05,
      "loss": 0.3939,
      "step": 1099
    },
    {
      "epoch": 7.62,
      "learning_rate": 9.782856285496495e-05,
      "loss": 0.4022,
      "step": 1100
    },
    {
      "epoch": 7.62,
      "learning_rate": 9.76838254615988e-05,
      "loss": 0.3908,
      "step": 1101
    },
    {
      "epoch": 7.63,
      "learning_rate": 9.75390929228107e-05,
      "loss": 0.3905,
      "step": 1102
    },
    {
      "epoch": 7.63,
      "learning_rate": 9.739436554195227e-05,
      "loss": 0.3875,
      "step": 1103
    },
    {
      "epoch": 7.63,
      "eval_loss": 0.47556066513061523,
      "eval_runtime": 28.1986,
      "eval_samples_per_second": 7.093,
      "eval_steps_per_second": 0.887,
      "step": 1103
    },
    {
      "epoch": 8.0,
      "learning_rate": 9.72496436223644e-05,
      "loss": 0.3972,
      "step": 1104
    },
    {
      "epoch": 8.01,
      "learning_rate": 9.710492746737643e-05,
      "loss": 0.3897,
      "step": 1105
    },
    {
      "epoch": 8.01,
      "learning_rate": 9.696021738030575e-05,
      "loss": 0.3939,
      "step": 1106
    },
    {
      "epoch": 8.02,
      "learning_rate": 9.681551366445694e-05,
      "loss": 0.3945,
      "step": 1107
    },
    {
      "epoch": 8.02,
      "learning_rate": 9.667081662312124e-05,
      "loss": 0.3993,
      "step": 1108
    },
    {
      "epoch": 8.03,
      "learning_rate": 9.652612655957596e-05,
      "loss": 0.3915,
      "step": 1109
    },
    {
      "epoch": 8.03,
      "learning_rate": 9.638144377708367e-05,
      "loss": 0.3993,
      "step": 1110
    },
    {
      "epoch": 8.04,
      "learning_rate": 9.62367685788918e-05,
      "loss": 0.3994,
      "step": 1111
    },
    {
      "epoch": 8.04,
      "learning_rate": 9.609210126823185e-05,
      "loss": 0.3963,
      "step": 1112
    },
    {
      "epoch": 8.05,
      "learning_rate": 9.59474421483187e-05,
      "loss": 0.3897,
      "step": 1113
    },
    {
      "epoch": 8.05,
      "learning_rate": 9.580279152235019e-05,
      "loss": 0.3982,
      "step": 1114
    },
    {
      "epoch": 8.06,
      "learning_rate": 9.565814969350629e-05,
      "loss": 0.3981,
      "step": 1115
    },
    {
      "epoch": 8.06,
      "learning_rate": 9.551351696494854e-05,
      "loss": 0.394,
      "step": 1116
    },
    {
      "epoch": 8.06,
      "learning_rate": 9.536889363981936e-05,
      "loss": 0.4008,
      "step": 1117
    },
    {
      "epoch": 8.07,
      "learning_rate": 9.522428002124157e-05,
      "loss": 0.3981,
      "step": 1118
    },
    {
      "epoch": 8.07,
      "learning_rate": 9.507967641231756e-05,
      "loss": 0.3999,
      "step": 1119
    },
    {
      "epoch": 8.08,
      "learning_rate": 9.493508311612874e-05,
      "loss": 0.3974,
      "step": 1120
    },
    {
      "epoch": 8.08,
      "learning_rate": 9.479050043573497e-05,
      "loss": 0.4002,
      "step": 1121
    },
    {
      "epoch": 8.09,
      "learning_rate": 9.46459286741738e-05,
      "loss": 0.3947,
      "step": 1122
    },
    {
      "epoch": 8.09,
      "learning_rate": 9.450136813445994e-05,
      "loss": 0.3945,
      "step": 1123
    },
    {
      "epoch": 8.1,
      "learning_rate": 9.43568191195845e-05,
      "loss": 0.3955,
      "step": 1124
    },
    {
      "epoch": 8.1,
      "learning_rate": 9.421228193251452e-05,
      "loss": 0.3937,
      "step": 1125
    },
    {
      "epoch": 8.11,
      "learning_rate": 9.406775687619223e-05,
      "loss": 0.3938,
      "step": 1126
    },
    {
      "epoch": 8.11,
      "learning_rate": 9.39232442535344e-05,
      "loss": 0.3895,
      "step": 1127
    },
    {
      "epoch": 8.11,
      "learning_rate": 9.377874436743184e-05,
      "loss": 0.394,
      "step": 1128
    },
    {
      "epoch": 8.12,
      "learning_rate": 9.363425752074844e-05,
      "loss": 0.3909,
      "step": 1129
    },
    {
      "epoch": 8.12,
      "learning_rate": 9.348978401632101e-05,
      "loss": 0.397,
      "step": 1130
    },
    {
      "epoch": 8.13,
      "learning_rate": 9.334532415695824e-05,
      "loss": 0.3906,
      "step": 1131
    },
    {
      "epoch": 8.13,
      "learning_rate": 9.320087824544031e-05,
      "loss": 0.3944,
      "step": 1132
    },
    {
      "epoch": 8.14,
      "learning_rate": 9.305644658451813e-05,
      "loss": 0.3941,
      "step": 1133
    },
    {
      "epoch": 8.14,
      "learning_rate": 9.291202947691271e-05,
      "loss": 0.3929,
      "step": 1134
    },
    {
      "epoch": 8.15,
      "learning_rate": 9.276762722531463e-05,
      "loss": 0.3929,
      "step": 1135
    },
    {
      "epoch": 8.15,
      "learning_rate": 9.262324013238325e-05,
      "loss": 0.3959,
      "step": 1136
    },
    {
      "epoch": 8.16,
      "learning_rate": 9.247886850074622e-05,
      "loss": 0.3941,
      "step": 1137
    },
    {
      "epoch": 8.16,
      "learning_rate": 9.233451263299875e-05,
      "loss": 0.3916,
      "step": 1138
    },
    {
      "epoch": 8.17,
      "learning_rate": 9.219017283170302e-05,
      "loss": 0.3891,
      "step": 1139
    },
    {
      "epoch": 8.17,
      "learning_rate": 9.204584939938762e-05,
      "loss": 0.3934,
      "step": 1140
    },
    {
      "epoch": 8.17,
      "learning_rate": 9.19015426385466e-05,
      "loss": 0.3918,
      "step": 1141
    },
    {
      "epoch": 8.18,
      "learning_rate": 9.175725285163932e-05,
      "loss": 0.3883,
      "step": 1142
    },
    {
      "epoch": 8.18,
      "learning_rate": 9.161298034108941e-05,
      "loss": 0.3926,
      "step": 1143
    },
    {
      "epoch": 8.19,
      "learning_rate": 9.146872540928437e-05,
      "loss": 0.3964,
      "step": 1144
    },
    {
      "epoch": 8.19,
      "learning_rate": 9.132448835857483e-05,
      "loss": 0.3939,
      "step": 1145
    },
    {
      "epoch": 8.2,
      "learning_rate": 9.118026949127389e-05,
      "loss": 0.3945,
      "step": 1146
    },
    {
      "epoch": 8.2,
      "learning_rate": 9.103606910965666e-05,
      "loss": 0.3953,
      "step": 1147
    },
    {
      "epoch": 8.21,
      "learning_rate": 9.089188751595936e-05,
      "loss": 0.3906,
      "step": 1148
    },
    {
      "epoch": 8.21,
      "learning_rate": 9.074772501237897e-05,
      "loss": 0.3933,
      "step": 1149
    },
    {
      "epoch": 8.22,
      "learning_rate": 9.060358190107234e-05,
      "loss": 0.3933,
      "step": 1150
    },
    {
      "epoch": 8.22,
      "learning_rate": 9.045945848415573e-05,
      "loss": 0.3858,
      "step": 1151
    },
    {
      "epoch": 8.23,
      "learning_rate": 9.031535506370417e-05,
      "loss": 0.3883,
      "step": 1152
    },
    {
      "epoch": 8.23,
      "learning_rate": 9.017127194175068e-05,
      "loss": 0.3885,
      "step": 1153
    },
    {
      "epoch": 8.23,
      "learning_rate": 9.002720942028577e-05,
      "loss": 0.3952,
      "step": 1154
    },
    {
      "epoch": 8.24,
      "learning_rate": 8.98831678012568e-05,
      "loss": 0.3939,
      "step": 1155
    },
    {
      "epoch": 8.24,
      "learning_rate": 8.97391473865673e-05,
      "loss": 0.3893,
      "step": 1156
    },
    {
      "epoch": 8.25,
      "learning_rate": 8.959514847807639e-05,
      "loss": 0.3895,
      "step": 1157
    },
    {
      "epoch": 8.25,
      "learning_rate": 8.945117137759802e-05,
      "loss": 0.392,
      "step": 1158
    },
    {
      "epoch": 8.26,
      "learning_rate": 8.930721638690056e-05,
      "loss": 0.385,
      "step": 1159
    },
    {
      "epoch": 8.26,
      "learning_rate": 8.916328380770595e-05,
      "loss": 0.3933,
      "step": 1160
    },
    {
      "epoch": 8.27,
      "learning_rate": 8.901937394168917e-05,
      "loss": 0.3954,
      "step": 1161
    },
    {
      "epoch": 8.27,
      "learning_rate": 8.887548709047764e-05,
      "loss": 0.3983,
      "step": 1162
    },
    {
      "epoch": 8.28,
      "learning_rate": 8.873162355565046e-05,
      "loss": 0.3864,
      "step": 1163
    },
    {
      "epoch": 8.28,
      "learning_rate": 8.858778363873796e-05,
      "loss": 0.386,
      "step": 1164
    },
    {
      "epoch": 8.28,
      "learning_rate": 8.844396764122093e-05,
      "loss": 0.3981,
      "step": 1165
    },
    {
      "epoch": 8.29,
      "learning_rate": 8.830017586452993e-05,
      "loss": 0.3939,
      "step": 1166
    },
    {
      "epoch": 8.29,
      "learning_rate": 8.815640861004488e-05,
      "loss": 0.3939,
      "step": 1167
    },
    {
      "epoch": 8.3,
      "learning_rate": 8.801266617909427e-05,
      "loss": 0.3859,
      "step": 1168
    },
    {
      "epoch": 8.3,
      "learning_rate": 8.786894887295451e-05,
      "loss": 0.3954,
      "step": 1169
    },
    {
      "epoch": 8.31,
      "learning_rate": 8.772525699284946e-05,
      "loss": 0.3909,
      "step": 1170
    },
    {
      "epoch": 8.31,
      "learning_rate": 8.75815908399496e-05,
      "loss": 0.3878,
      "step": 1171
    },
    {
      "epoch": 8.32,
      "learning_rate": 8.743795071537146e-05,
      "loss": 0.3881,
      "step": 1172
    },
    {
      "epoch": 8.32,
      "learning_rate": 8.729433692017711e-05,
      "loss": 0.3908,
      "step": 1173
    },
    {
      "epoch": 8.33,
      "learning_rate": 8.715074975537338e-05,
      "loss": 0.3899,
      "step": 1174
    },
    {
      "epoch": 8.33,
      "learning_rate": 8.700718952191124e-05,
      "loss": 0.397,
      "step": 1175
    },
    {
      "epoch": 8.34,
      "learning_rate": 8.686365652068535e-05,
      "loss": 0.3852,
      "step": 1176
    },
    {
      "epoch": 8.34,
      "learning_rate": 8.672015105253319e-05,
      "loss": 0.3877,
      "step": 1177
    },
    {
      "epoch": 8.34,
      "learning_rate": 8.657667341823448e-05,
      "loss": 0.393,
      "step": 1178
    },
    {
      "epoch": 8.35,
      "learning_rate": 8.643322391851072e-05,
      "loss": 0.3941,
      "step": 1179
    },
    {
      "epoch": 8.35,
      "learning_rate": 8.628980285402439e-05,
      "loss": 0.3949,
      "step": 1180
    },
    {
      "epoch": 8.36,
      "learning_rate": 8.614641052537838e-05,
      "loss": 0.3884,
      "step": 1181
    },
    {
      "epoch": 8.36,
      "learning_rate": 8.600304723311534e-05,
      "loss": 0.3872,
      "step": 1182
    },
    {
      "epoch": 8.37,
      "learning_rate": 8.585971327771707e-05,
      "loss": 0.3789,
      "step": 1183
    },
    {
      "epoch": 8.37,
      "learning_rate": 8.571640895960387e-05,
      "loss": 0.3925,
      "step": 1184
    },
    {
      "epoch": 8.38,
      "learning_rate": 8.557313457913394e-05,
      "loss": 0.3883,
      "step": 1185
    },
    {
      "epoch": 8.38,
      "learning_rate": 8.54298904366027e-05,
      "loss": 0.3875,
      "step": 1186
    },
    {
      "epoch": 8.39,
      "learning_rate": 8.528667683224225e-05,
      "loss": 0.3867,
      "step": 1187
    },
    {
      "epoch": 8.39,
      "learning_rate": 8.514349406622064e-05,
      "loss": 0.3839,
      "step": 1188
    },
    {
      "epoch": 8.39,
      "learning_rate": 8.50003424386413e-05,
      "loss": 0.393,
      "step": 1189
    },
    {
      "epoch": 8.4,
      "learning_rate": 8.485722224954237e-05,
      "loss": 0.3953,
      "step": 1190
    },
    {
      "epoch": 8.4,
      "learning_rate": 8.471413379889609e-05,
      "loss": 0.3903,
      "step": 1191
    },
    {
      "epoch": 8.41,
      "learning_rate": 8.457107738660826e-05,
      "loss": 0.3897,
      "step": 1192
    },
    {
      "epoch": 8.41,
      "learning_rate": 8.44280533125174e-05,
      "loss": 0.3942,
      "step": 1193
    },
    {
      "epoch": 8.42,
      "learning_rate": 8.428506187639443e-05,
      "loss": 0.3957,
      "step": 1194
    },
    {
      "epoch": 8.42,
      "learning_rate": 8.414210337794166e-05,
      "loss": 0.3908,
      "step": 1195
    },
    {
      "epoch": 8.43,
      "learning_rate": 8.39991781167925e-05,
      "loss": 0.3829,
      "step": 1196
    },
    {
      "epoch": 8.43,
      "learning_rate": 8.385628639251066e-05,
      "loss": 0.3885,
      "step": 1197
    },
    {
      "epoch": 8.44,
      "learning_rate": 8.371342850458955e-05,
      "loss": 0.388,
      "step": 1198
    },
    {
      "epoch": 8.44,
      "learning_rate": 8.357060475245166e-05,
      "loss": 0.3863,
      "step": 1199
    },
    {
      "epoch": 8.45,
      "learning_rate": 8.342781543544798e-05,
      "loss": 0.3897,
      "step": 1200
    },
    {
      "epoch": 8.45,
      "learning_rate": 8.328506085285724e-05,
      "loss": 0.389,
      "step": 1201
    },
    {
      "epoch": 8.45,
      "learning_rate": 8.31423413038854e-05,
      "loss": 0.3897,
      "step": 1202
    },
    {
      "epoch": 8.46,
      "learning_rate": 8.299965708766505e-05,
      "loss": 0.3896,
      "step": 1203
    },
    {
      "epoch": 8.46,
      "learning_rate": 8.285700850325467e-05,
      "loss": 0.3903,
      "step": 1204
    },
    {
      "epoch": 8.47,
      "learning_rate": 8.271439584963802e-05,
      "loss": 0.392,
      "step": 1205
    },
    {
      "epoch": 8.47,
      "learning_rate": 8.257181942572365e-05,
      "loss": 0.3932,
      "step": 1206
    },
    {
      "epoch": 8.48,
      "learning_rate": 8.242927953034412e-05,
      "loss": 0.3879,
      "step": 1207
    },
    {
      "epoch": 8.48,
      "learning_rate": 8.22867764622554e-05,
      "loss": 0.3923,
      "step": 1208
    },
    {
      "epoch": 8.49,
      "learning_rate": 8.214431052013634e-05,
      "loss": 0.3884,
      "step": 1209
    },
    {
      "epoch": 8.49,
      "learning_rate": 8.200188200258791e-05,
      "loss": 0.3855,
      "step": 1210
    },
    {
      "epoch": 8.5,
      "learning_rate": 8.18594912081327e-05,
      "loss": 0.3859,
      "step": 1211
    },
    {
      "epoch": 8.5,
      "learning_rate": 8.171713843521418e-05,
      "loss": 0.3871,
      "step": 1212
    },
    {
      "epoch": 8.51,
      "learning_rate": 8.157482398219613e-05,
      "loss": 0.3807,
      "step": 1213
    },
    {
      "epoch": 8.51,
      "learning_rate": 8.143254814736211e-05,
      "loss": 0.3863,
      "step": 1214
    },
    {
      "epoch": 8.51,
      "learning_rate": 8.129031122891459e-05,
      "loss": 0.3901,
      "step": 1215
    },
    {
      "epoch": 8.52,
      "learning_rate": 8.114811352497458e-05,
      "loss": 0.3927,
      "step": 1216
    },
    {
      "epoch": 8.52,
      "learning_rate": 8.100595533358084e-05,
      "loss": 0.3809,
      "step": 1217
    },
    {
      "epoch": 8.53,
      "learning_rate": 8.086383695268938e-05,
      "loss": 0.3854,
      "step": 1218
    },
    {
      "epoch": 8.53,
      "learning_rate": 8.072175868017268e-05,
      "loss": 0.3926,
      "step": 1219
    },
    {
      "epoch": 8.54,
      "learning_rate": 8.057972081381927e-05,
      "loss": 0.3955,
      "step": 1220
    },
    {
      "epoch": 8.54,
      "learning_rate": 8.043772365133287e-05,
      "loss": 0.388,
      "step": 1221
    },
    {
      "epoch": 8.55,
      "learning_rate": 8.029576749033194e-05,
      "loss": 0.3881,
      "step": 1222
    },
    {
      "epoch": 8.55,
      "learning_rate": 8.015385262834906e-05,
      "loss": 0.3888,
      "step": 1223
    },
    {
      "epoch": 8.56,
      "learning_rate": 8.001197936283014e-05,
      "loss": 0.3851,
      "step": 1224
    },
    {
      "epoch": 8.56,
      "learning_rate": 7.987014799113397e-05,
      "loss": 0.3905,
      "step": 1225
    },
    {
      "epoch": 8.56,
      "learning_rate": 7.972835881053159e-05,
      "loss": 0.3913,
      "step": 1226
    },
    {
      "epoch": 8.57,
      "learning_rate": 7.958661211820545e-05,
      "loss": 0.3884,
      "step": 1227
    },
    {
      "epoch": 8.57,
      "learning_rate": 7.944490821124908e-05,
      "loss": 0.3938,
      "step": 1228
    },
    {
      "epoch": 8.58,
      "learning_rate": 7.930324738666627e-05,
      "loss": 0.3892,
      "step": 1229
    },
    {
      "epoch": 8.58,
      "learning_rate": 7.916162994137056e-05,
      "loss": 0.3819,
      "step": 1230
    },
    {
      "epoch": 8.59,
      "learning_rate": 7.902005617218454e-05,
      "loss": 0.3874,
      "step": 1231
    },
    {
      "epoch": 8.59,
      "learning_rate": 7.887852637583926e-05,
      "loss": 0.3873,
      "step": 1232
    },
    {
      "epoch": 8.6,
      "learning_rate": 7.873704084897365e-05,
      "loss": 0.3865,
      "step": 1233
    },
    {
      "epoch": 8.6,
      "learning_rate": 7.85955998881337e-05,
      "loss": 0.3914,
      "step": 1234
    },
    {
      "epoch": 8.61,
      "learning_rate": 7.845420378977223e-05,
      "loss": 0.3866,
      "step": 1235
    },
    {
      "epoch": 8.61,
      "learning_rate": 7.831285285024781e-05,
      "loss": 0.3829,
      "step": 1236
    },
    {
      "epoch": 8.62,
      "learning_rate": 7.817154736582452e-05,
      "loss": 0.383,
      "step": 1237
    },
    {
      "epoch": 8.62,
      "learning_rate": 7.803028763267108e-05,
      "loss": 0.3942,
      "step": 1238
    },
    {
      "epoch": 8.62,
      "learning_rate": 7.788907394686033e-05,
      "loss": 0.3779,
      "step": 1239
    },
    {
      "epoch": 8.63,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.3832,
      "step": 1240
    },
    {
      "epoch": 8.63,
      "eval_loss": 0.4780256748199463,
      "eval_runtime": 28.2756,
      "eval_samples_per_second": 7.073,
      "eval_steps_per_second": 0.884,
      "step": 1240
    },
    {
      "epoch": 9.0,
      "learning_rate": 7.760678590107507e-05,
      "loss": 0.3799,
      "step": 1241
    },
    {
      "epoch": 9.01,
      "learning_rate": 7.746571213276125e-05,
      "loss": 0.3877,
      "step": 1242
    },
    {
      "epoch": 9.01,
      "learning_rate": 7.732468559511016e-05,
      "loss": 0.3894,
      "step": 1243
    },
    {
      "epoch": 9.01,
      "learning_rate": 7.718370658370596e-05,
      "loss": 0.3867,
      "step": 1244
    },
    {
      "epoch": 9.02,
      "learning_rate": 7.704277539403304e-05,
      "loss": 0.3849,
      "step": 1245
    },
    {
      "epoch": 9.02,
      "learning_rate": 7.690189232147566e-05,
      "loss": 0.3834,
      "step": 1246
    },
    {
      "epoch": 9.03,
      "learning_rate": 7.676105766131726e-05,
      "loss": 0.3855,
      "step": 1247
    },
    {
      "epoch": 9.03,
      "learning_rate": 7.66202717087397e-05,
      "loss": 0.3831,
      "step": 1248
    },
    {
      "epoch": 9.04,
      "learning_rate": 7.647953475882285e-05,
      "loss": 0.3849,
      "step": 1249
    },
    {
      "epoch": 9.04,
      "learning_rate": 7.633884710654383e-05,
      "loss": 0.3867,
      "step": 1250
    },
    {
      "epoch": 9.05,
      "learning_rate": 7.619820904677641e-05,
      "loss": 0.3883,
      "step": 1251
    },
    {
      "epoch": 9.05,
      "learning_rate": 7.605762087429044e-05,
      "loss": 0.3872,
      "step": 1252
    },
    {
      "epoch": 9.06,
      "learning_rate": 7.591708288375125e-05,
      "loss": 0.3896,
      "step": 1253
    },
    {
      "epoch": 9.06,
      "learning_rate": 7.577659536971895e-05,
      "loss": 0.3916,
      "step": 1254
    },
    {
      "epoch": 9.06,
      "learning_rate": 7.56361586266478e-05,
      "loss": 0.3898,
      "step": 1255
    },
    {
      "epoch": 9.07,
      "learning_rate": 7.549577294888581e-05,
      "loss": 0.3884,
      "step": 1256
    },
    {
      "epoch": 9.07,
      "learning_rate": 7.535543863067377e-05,
      "loss": 0.391,
      "step": 1257
    },
    {
      "epoch": 9.08,
      "learning_rate": 7.521515596614496e-05,
      "loss": 0.3867,
      "step": 1258
    },
    {
      "epoch": 9.08,
      "learning_rate": 7.507492524932433e-05,
      "loss": 0.3866,
      "step": 1259
    },
    {
      "epoch": 9.09,
      "learning_rate": 7.493474677412794e-05,
      "loss": 0.3903,
      "step": 1260
    },
    {
      "epoch": 9.09,
      "learning_rate": 7.479462083436241e-05,
      "loss": 0.3917,
      "step": 1261
    },
    {
      "epoch": 9.1,
      "learning_rate": 7.465454772372425e-05,
      "loss": 0.3833,
      "step": 1262
    },
    {
      "epoch": 9.1,
      "learning_rate": 7.451452773579915e-05,
      "loss": 0.3872,
      "step": 1263
    },
    {
      "epoch": 9.11,
      "learning_rate": 7.437456116406152e-05,
      "loss": 0.385,
      "step": 1264
    },
    {
      "epoch": 9.11,
      "learning_rate": 7.423464830187386e-05,
      "loss": 0.3861,
      "step": 1265
    },
    {
      "epoch": 9.12,
      "learning_rate": 7.409478944248602e-05,
      "loss": 0.3788,
      "step": 1266
    },
    {
      "epoch": 9.12,
      "learning_rate": 7.39549848790347e-05,
      "loss": 0.3886,
      "step": 1267
    },
    {
      "epoch": 9.12,
      "learning_rate": 7.381523490454278e-05,
      "loss": 0.3845,
      "step": 1268
    },
    {
      "epoch": 9.13,
      "learning_rate": 7.367553981191875e-05,
      "loss": 0.3844,
      "step": 1269
    },
    {
      "epoch": 9.13,
      "learning_rate": 7.353589989395604e-05,
      "loss": 0.3828,
      "step": 1270
    },
    {
      "epoch": 9.14,
      "learning_rate": 7.339631544333249e-05,
      "loss": 0.3886,
      "step": 1271
    },
    {
      "epoch": 9.14,
      "learning_rate": 7.325678675260961e-05,
      "loss": 0.3829,
      "step": 1272
    },
    {
      "epoch": 9.15,
      "learning_rate": 7.31173141142321e-05,
      "loss": 0.3859,
      "step": 1273
    },
    {
      "epoch": 9.15,
      "learning_rate": 7.297789782052717e-05,
      "loss": 0.3829,
      "step": 1274
    },
    {
      "epoch": 9.16,
      "learning_rate": 7.283853816370386e-05,
      "loss": 0.387,
      "step": 1275
    },
    {
      "epoch": 9.16,
      "learning_rate": 7.269923543585258e-05,
      "loss": 0.38,
      "step": 1276
    },
    {
      "epoch": 9.17,
      "learning_rate": 7.255998992894443e-05,
      "loss": 0.3875,
      "step": 1277
    },
    {
      "epoch": 9.17,
      "learning_rate": 7.242080193483051e-05,
      "loss": 0.3846,
      "step": 1278
    },
    {
      "epoch": 9.18,
      "learning_rate": 7.228167174524148e-05,
      "loss": 0.3852,
      "step": 1279
    },
    {
      "epoch": 9.18,
      "learning_rate": 7.214259965178674e-05,
      "loss": 0.3833,
      "step": 1280
    },
    {
      "epoch": 9.18,
      "learning_rate": 7.200358594595392e-05,
      "loss": 0.3797,
      "step": 1281
    },
    {
      "epoch": 9.19,
      "learning_rate": 7.186463091910838e-05,
      "loss": 0.3818,
      "step": 1282
    },
    {
      "epoch": 9.19,
      "learning_rate": 7.172573486249241e-05,
      "loss": 0.3867,
      "step": 1283
    },
    {
      "epoch": 9.2,
      "learning_rate": 7.15868980672247e-05,
      "loss": 0.3807,
      "step": 1284
    },
    {
      "epoch": 9.2,
      "learning_rate": 7.14481208242998e-05,
      "loss": 0.384,
      "step": 1285
    },
    {
      "epoch": 9.21,
      "learning_rate": 7.130940342458732e-05,
      "loss": 0.3863,
      "step": 1286
    },
    {
      "epoch": 9.21,
      "learning_rate": 7.117074615883162e-05,
      "loss": 0.3842,
      "step": 1287
    },
    {
      "epoch": 9.22,
      "learning_rate": 7.10321493176508e-05,
      "loss": 0.385,
      "step": 1288
    },
    {
      "epoch": 9.22,
      "learning_rate": 7.089361319153649e-05,
      "loss": 0.3844,
      "step": 1289
    },
    {
      "epoch": 9.23,
      "learning_rate": 7.075513807085299e-05,
      "loss": 0.3841,
      "step": 1290
    },
    {
      "epoch": 9.23,
      "learning_rate": 7.061672424583677e-05,
      "loss": 0.3828,
      "step": 1291
    },
    {
      "epoch": 9.23,
      "learning_rate": 7.047837200659579e-05,
      "loss": 0.3814,
      "step": 1292
    },
    {
      "epoch": 9.24,
      "learning_rate": 7.034008164310892e-05,
      "loss": 0.3807,
      "step": 1293
    },
    {
      "epoch": 9.24,
      "learning_rate": 7.020185344522543e-05,
      "loss": 0.3787,
      "step": 1294
    },
    {
      "epoch": 9.25,
      "learning_rate": 7.006368770266421e-05,
      "loss": 0.3809,
      "step": 1295
    },
    {
      "epoch": 9.25,
      "learning_rate": 6.992558470501325e-05,
      "loss": 0.3784,
      "step": 1296
    },
    {
      "epoch": 9.26,
      "learning_rate": 6.978754474172909e-05,
      "loss": 0.3808,
      "step": 1297
    },
    {
      "epoch": 9.26,
      "learning_rate": 6.964956810213605e-05,
      "loss": 0.3788,
      "step": 1298
    },
    {
      "epoch": 9.27,
      "learning_rate": 6.95116550754259e-05,
      "loss": 0.3927,
      "step": 1299
    },
    {
      "epoch": 9.27,
      "learning_rate": 6.937380595065685e-05,
      "loss": 0.3848,
      "step": 1300
    },
    {
      "epoch": 9.28,
      "learning_rate": 6.923602101675337e-05,
      "loss": 0.3848,
      "step": 1301
    },
    {
      "epoch": 9.28,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.3805,
      "step": 1302
    },
    {
      "epoch": 9.29,
      "learning_rate": 6.89606448765673e-05,
      "loss": 0.3786,
      "step": 1303
    },
    {
      "epoch": 9.29,
      "learning_rate": 6.88230542474584e-05,
      "loss": 0.3823,
      "step": 1304
    },
    {
      "epoch": 9.29,
      "learning_rate": 6.868552896356117e-05,
      "loss": 0.3795,
      "step": 1305
    },
    {
      "epoch": 9.3,
      "learning_rate": 6.854806931312128e-05,
      "loss": 0.3875,
      "step": 1306
    },
    {
      "epoch": 9.3,
      "learning_rate": 6.841067558424677e-05,
      "loss": 0.3849,
      "step": 1307
    },
    {
      "epoch": 9.31,
      "learning_rate": 6.827334806490757e-05,
      "loss": 0.3856,
      "step": 1308
    },
    {
      "epoch": 9.31,
      "learning_rate": 6.813608704293484e-05,
      "loss": 0.3851,
      "step": 1309
    },
    {
      "epoch": 9.32,
      "learning_rate": 6.799889280602031e-05,
      "loss": 0.379,
      "step": 1310
    },
    {
      "epoch": 9.32,
      "learning_rate": 6.786176564171582e-05,
      "loss": 0.3843,
      "step": 1311
    },
    {
      "epoch": 9.33,
      "learning_rate": 6.77247058374325e-05,
      "loss": 0.3855,
      "step": 1312
    },
    {
      "epoch": 9.33,
      "learning_rate": 6.758771368044042e-05,
      "loss": 0.3795,
      "step": 1313
    },
    {
      "epoch": 9.34,
      "learning_rate": 6.74507894578678e-05,
      "loss": 0.3809,
      "step": 1314
    },
    {
      "epoch": 9.34,
      "learning_rate": 6.731393345670051e-05,
      "loss": 0.3858,
      "step": 1315
    },
    {
      "epoch": 9.35,
      "learning_rate": 6.717714596378137e-05,
      "loss": 0.3788,
      "step": 1316
    },
    {
      "epoch": 9.35,
      "learning_rate": 6.704042726580972e-05,
      "loss": 0.3801,
      "step": 1317
    },
    {
      "epoch": 9.35,
      "learning_rate": 6.69037776493406e-05,
      "loss": 0.3835,
      "step": 1318
    },
    {
      "epoch": 9.36,
      "learning_rate": 6.67671974007843e-05,
      "loss": 0.3817,
      "step": 1319
    },
    {
      "epoch": 9.36,
      "learning_rate": 6.663068680640574e-05,
      "loss": 0.3846,
      "step": 1320
    },
    {
      "epoch": 9.37,
      "learning_rate": 6.649424615232382e-05,
      "loss": 0.3826,
      "step": 1321
    },
    {
      "epoch": 9.37,
      "learning_rate": 6.635787572451083e-05,
      "loss": 0.379,
      "step": 1322
    },
    {
      "epoch": 9.38,
      "learning_rate": 6.622157580879195e-05,
      "loss": 0.3808,
      "step": 1323
    },
    {
      "epoch": 9.38,
      "learning_rate": 6.608534669084449e-05,
      "loss": 0.3782,
      "step": 1324
    },
    {
      "epoch": 9.39,
      "learning_rate": 6.59491886561974e-05,
      "loss": 0.386,
      "step": 1325
    },
    {
      "epoch": 9.39,
      "learning_rate": 6.58131019902306e-05,
      "loss": 0.3801,
      "step": 1326
    },
    {
      "epoch": 9.4,
      "learning_rate": 6.567708697817453e-05,
      "loss": 0.3838,
      "step": 1327
    },
    {
      "epoch": 9.4,
      "learning_rate": 6.554114390510935e-05,
      "loss": 0.379,
      "step": 1328
    },
    {
      "epoch": 9.4,
      "learning_rate": 6.540527305596449e-05,
      "loss": 0.3781,
      "step": 1329
    },
    {
      "epoch": 9.41,
      "learning_rate": 6.526947471551798e-05,
      "loss": 0.3812,
      "step": 1330
    },
    {
      "epoch": 9.41,
      "learning_rate": 6.513374916839587e-05,
      "loss": 0.3787,
      "step": 1331
    },
    {
      "epoch": 9.42,
      "learning_rate": 6.499809669907169e-05,
      "loss": 0.3865,
      "step": 1332
    },
    {
      "epoch": 9.42,
      "learning_rate": 6.486251759186572e-05,
      "loss": 0.3822,
      "step": 1333
    },
    {
      "epoch": 9.43,
      "learning_rate": 6.472701213094456e-05,
      "loss": 0.3791,
      "step": 1334
    },
    {
      "epoch": 9.43,
      "learning_rate": 6.45915806003204e-05,
      "loss": 0.3839,
      "step": 1335
    },
    {
      "epoch": 9.44,
      "learning_rate": 6.445622328385047e-05,
      "loss": 0.3788,
      "step": 1336
    },
    {
      "epoch": 9.44,
      "learning_rate": 6.432094046523646e-05,
      "loss": 0.3763,
      "step": 1337
    },
    {
      "epoch": 9.45,
      "learning_rate": 6.418573242802397e-05,
      "loss": 0.3868,
      "step": 1338
    },
    {
      "epoch": 9.45,
      "learning_rate": 6.405059945560179e-05,
      "loss": 0.3823,
      "step": 1339
    },
    {
      "epoch": 9.46,
      "learning_rate": 6.391554183120138e-05,
      "loss": 0.3752,
      "step": 1340
    },
    {
      "epoch": 9.46,
      "learning_rate": 6.378055983789637e-05,
      "loss": 0.3808,
      "step": 1341
    },
    {
      "epoch": 9.46,
      "learning_rate": 6.364565375860174e-05,
      "loss": 0.3863,
      "step": 1342
    },
    {
      "epoch": 9.47,
      "learning_rate": 6.351082387607345e-05,
      "loss": 0.3849,
      "step": 1343
    },
    {
      "epoch": 9.47,
      "learning_rate": 6.337607047290774e-05,
      "loss": 0.3801,
      "step": 1344
    },
    {
      "epoch": 9.48,
      "learning_rate": 6.324139383154049e-05,
      "loss": 0.3777,
      "step": 1345
    },
    {
      "epoch": 9.48,
      "learning_rate": 6.310679423424679e-05,
      "loss": 0.3814,
      "step": 1346
    },
    {
      "epoch": 9.49,
      "learning_rate": 6.297227196314018e-05,
      "loss": 0.3865,
      "step": 1347
    },
    {
      "epoch": 9.49,
      "learning_rate": 6.283782730017218e-05,
      "loss": 0.3758,
      "step": 1348
    },
    {
      "epoch": 9.5,
      "learning_rate": 6.270346052713154e-05,
      "loss": 0.3815,
      "step": 1349
    },
    {
      "epoch": 9.5,
      "learning_rate": 6.25691719256439e-05,
      "loss": 0.3797,
      "step": 1350
    },
    {
      "epoch": 9.51,
      "learning_rate": 6.243496177717099e-05,
      "loss": 0.3763,
      "step": 1351
    },
    {
      "epoch": 9.51,
      "learning_rate": 6.230083036301004e-05,
      "loss": 0.3775,
      "step": 1352
    },
    {
      "epoch": 9.51,
      "learning_rate": 6.216677796429342e-05,
      "loss": 0.3753,
      "step": 1353
    },
    {
      "epoch": 9.52,
      "learning_rate": 6.20328048619877e-05,
      "loss": 0.3835,
      "step": 1354
    },
    {
      "epoch": 9.52,
      "learning_rate": 6.189891133689342e-05,
      "loss": 0.3751,
      "step": 1355
    },
    {
      "epoch": 9.53,
      "learning_rate": 6.176509766964421e-05,
      "loss": 0.3806,
      "step": 1356
    },
    {
      "epoch": 9.53,
      "learning_rate": 6.163136414070635e-05,
      "loss": 0.3853,
      "step": 1357
    },
    {
      "epoch": 9.54,
      "learning_rate": 6.149771103037821e-05,
      "loss": 0.3844,
      "step": 1358
    },
    {
      "epoch": 9.54,
      "learning_rate": 6.136413861878953e-05,
      "loss": 0.3819,
      "step": 1359
    },
    {
      "epoch": 9.55,
      "learning_rate": 6.123064718590099e-05,
      "loss": 0.3771,
      "step": 1360
    },
    {
      "epoch": 9.55,
      "learning_rate": 6.10972370115034e-05,
      "loss": 0.3866,
      "step": 1361
    },
    {
      "epoch": 9.56,
      "learning_rate": 6.096390837521746e-05,
      "loss": 0.3799,
      "step": 1362
    },
    {
      "epoch": 9.56,
      "learning_rate": 6.0830661556492806e-05,
      "loss": 0.3767,
      "step": 1363
    },
    {
      "epoch": 9.57,
      "learning_rate": 6.069749683460765e-05,
      "loss": 0.3779,
      "step": 1364
    },
    {
      "epoch": 9.57,
      "learning_rate": 6.0564414488668165e-05,
      "loss": 0.3843,
      "step": 1365
    },
    {
      "epoch": 9.57,
      "learning_rate": 6.043141479760778e-05,
      "loss": 0.3739,
      "step": 1366
    },
    {
      "epoch": 9.58,
      "learning_rate": 6.0298498040186794e-05,
      "loss": 0.3831,
      "step": 1367
    },
    {
      "epoch": 9.58,
      "learning_rate": 6.0165664494991594e-05,
      "loss": 0.3801,
      "step": 1368
    },
    {
      "epoch": 9.59,
      "learning_rate": 6.0032914440434186e-05,
      "loss": 0.3844,
      "step": 1369
    },
    {
      "epoch": 9.59,
      "learning_rate": 5.9900248154751616e-05,
      "loss": 0.3854,
      "step": 1370
    },
    {
      "epoch": 9.6,
      "learning_rate": 5.9767665916005286e-05,
      "loss": 0.382,
      "step": 1371
    },
    {
      "epoch": 9.6,
      "learning_rate": 5.9635168002080564e-05,
      "loss": 0.3805,
      "step": 1372
    },
    {
      "epoch": 9.61,
      "learning_rate": 5.950275469068588e-05,
      "loss": 0.3775,
      "step": 1373
    },
    {
      "epoch": 9.61,
      "learning_rate": 5.937042625935252e-05,
      "loss": 0.379,
      "step": 1374
    },
    {
      "epoch": 9.62,
      "learning_rate": 5.923818298543379e-05,
      "loss": 0.3786,
      "step": 1375
    },
    {
      "epoch": 9.62,
      "learning_rate": 5.9106025146104525e-05,
      "loss": 0.3797,
      "step": 1376
    },
    {
      "epoch": 9.63,
      "learning_rate": 5.897395301836051e-05,
      "loss": 0.3748,
      "step": 1377
    },
    {
      "epoch": 9.63,
      "learning_rate": 5.8841966879017816e-05,
      "loss": 0.3682,
      "step": 1378
    },
    {
      "epoch": 9.63,
      "eval_loss": 0.4814474880695343,
      "eval_runtime": 28.2712,
      "eval_samples_per_second": 7.074,
      "eval_steps_per_second": 0.884,
      "step": 1378
    },
    {
      "epoch": 9.63,
      "step": 1378,
      "total_flos": 5.88729111501865e+16,
      "train_loss": 0.4462547982638737,
      "train_runtime": 110414.5531,
      "train_samples_per_second": 2.524,
      "train_steps_per_second": 0.02
    }
  ],
  "logging_steps": 1,
  "max_steps": 2170,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 5.88729111501865e+16,
  "trial_name": null,
  "trial_params": null
}