{
  "best_metric": 0.8100082278251648,
  "best_model_checkpoint": "./lora-out/checkpoint-1408",
  "epoch": 1.9815340909090908,
  "eval_steps": 176,
  "global_step": 1408,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 1.0748,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.1153677701950073,
      "eval_runtime": 59.6311,
      "eval_samples_per_second": 6.708,
      "eval_steps_per_second": 3.354,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 1.1247,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-05,
      "loss": 1.1111,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 1.0777,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.033,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012,
      "loss": 1.0021,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014,
      "loss": 1.0017,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016,
      "loss": 1.0205,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018,
      "loss": 0.95,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.0236,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999974750358046,
      "loss": 0.9656,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999899001559682,
      "loss": 0.9769,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999772753987444,
      "loss": 0.984,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001999959600827887,
      "loss": 0.9227,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001999936876532651,
      "loss": 0.9342,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999091026277928,
      "loss": 0.991,
      "step": 16
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019998762792535683,
      "loss": 0.9632,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019998384065757335,
      "loss": 0.9574,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019997954847855427,
      "loss": 0.9778,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019997475140997475,
      "loss": 0.8948,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019996944947605968,
      "loss": 0.9359,
      "step": 21
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019996364270358346,
      "loss": 0.8931,
      "step": 22
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019995733112186982,
      "loss": 0.9468,
      "step": 23
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019995051476279186,
      "loss": 0.9246,
      "step": 24
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019994319366077167,
      "loss": 0.9223,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019993536785278032,
      "loss": 0.8973,
      "step": 26
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019992703737833748,
      "loss": 0.9316,
      "step": 27
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999182022795116,
      "loss": 0.9499,
      "step": 28
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019990886260091916,
      "loss": 0.9069,
      "step": 29
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019989901838972496,
      "loss": 0.9034,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001998886696956415,
      "loss": 0.9329,
      "step": 31
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000199877816570929,
      "loss": 0.944,
      "step": 32
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019986645907039497,
      "loss": 0.899,
      "step": 33
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001998545972513939,
      "loss": 0.8994,
      "step": 34
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019984223117382714,
      "loss": 0.88,
      "step": 35
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019982936090014256,
      "loss": 0.9321,
      "step": 36
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001998159864953341,
      "loss": 0.9437,
      "step": 37
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001998021080269415,
      "loss": 0.8879,
      "step": 38
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001997877255650501,
      "loss": 0.8921,
      "step": 39
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019977283918229022,
      "loss": 0.8943,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019975744895383706,
      "loss": 0.8991,
      "step": 41
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019974155495741024,
      "loss": 0.8881,
      "step": 42
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001997251572732732,
      "loss": 0.9018,
      "step": 43
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019970825598423315,
      "loss": 0.8722,
      "step": 44
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019969085117564034,
      "loss": 0.9355,
      "step": 45
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001996729429353878,
      "loss": 0.9524,
      "step": 46
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001996545313539109,
      "loss": 0.9006,
      "step": 47
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019963561652418683,
      "loss": 0.869,
      "step": 48
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001996161985417341,
      "loss": 0.8397,
      "step": 49
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019959627750461208,
      "loss": 0.8915,
      "step": 50
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001995758535134206,
      "loss": 0.8423,
      "step": 51
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001995549266712994,
      "loss": 0.8994,
      "step": 52
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019953349708392752,
      "loss": 0.8939,
      "step": 53
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001995115648595228,
      "loss": 0.93,
      "step": 54
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019948913010884147,
      "loss": 0.8913,
      "step": 55
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019946619294517736,
      "loss": 0.8927,
      "step": 56
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019944275348436153,
      "loss": 0.875,
      "step": 57
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019941881184476154,
      "loss": 0.8199,
      "step": 58
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000199394368147281,
      "loss": 0.9137,
      "step": 59
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019936942251535882,
      "loss": 0.8572,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019934397507496865,
      "loss": 0.9061,
      "step": 61
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019931802595461826,
      "loss": 0.9258,
      "step": 62
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001992915752853488,
      "loss": 0.945,
      "step": 63
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019926462320073429,
      "loss": 0.8826,
      "step": 64
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019923716983688086,
      "loss": 0.8929,
      "step": 65
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019920921533242596,
      "loss": 0.8848,
      "step": 66
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019918075982853793,
      "loss": 0.9109,
      "step": 67
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001991518034689149,
      "loss": 0.9073,
      "step": 68
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019912234639978454,
      "loss": 0.9215,
      "step": 69
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019909238876990285,
      "loss": 0.8772,
      "step": 70
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019906193073055374,
      "loss": 0.8677,
      "step": 71
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019903097243554815,
      "loss": 0.8607,
      "step": 72
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019899951404122327,
      "loss": 0.8926,
      "step": 73
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019896755570644165,
      "loss": 0.8746,
      "step": 74
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019893509759259068,
      "loss": 0.8866,
      "step": 75
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019890213986358148,
      "loss": 0.853,
      "step": 76
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019886868268584822,
      "loss": 0.8957,
      "step": 77
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019883472622834723,
      "loss": 0.9247,
      "step": 78
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019880027066255623,
      "loss": 0.8831,
      "step": 79
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019876531616247337,
      "loss": 0.8998,
      "step": 80
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019872986290461633,
      "loss": 0.8242,
      "step": 81
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019869391106802154,
      "loss": 0.8815,
      "step": 82
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019865746083424317,
      "loss": 0.8705,
      "step": 83
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019862051238735232,
      "loss": 0.8767,
      "step": 84
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019858306591393602,
      "loss": 0.9376,
      "step": 85
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019854512160309625,
      "loss": 0.875,
      "step": 86
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019850667964644908,
      "loss": 0.8512,
      "step": 87
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019846774023812364,
      "loss": 0.8755,
      "step": 88
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019842830357476112,
      "loss": 0.8862,
      "step": 89
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001983883698555139,
      "loss": 0.8209,
      "step": 90
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019834793928204435,
      "loss": 0.8633,
      "step": 91
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000198307012058524,
      "loss": 0.8421,
      "step": 92
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019826558839163236,
      "loss": 0.8771,
      "step": 93
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019822366849055602,
      "loss": 0.8392,
      "step": 94
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001981812525669875,
      "loss": 0.8565,
      "step": 95
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019813834083512414,
      "loss": 0.8965,
      "step": 96
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019809493351166711,
      "loss": 0.8669,
      "step": 97
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001980510308158203,
      "loss": 0.8476,
      "step": 98
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019800663296928918,
      "loss": 0.8604,
      "step": 99
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001979617401962797,
      "loss": 0.8687,
      "step": 100
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001979163527234971,
      "loss": 0.8716,
      "step": 101
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019787047078014496,
      "loss": 0.8727,
      "step": 102
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019782409459792371,
      "loss": 0.8484,
      "step": 103
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019777722441102985,
      "loss": 0.8811,
      "step": 104
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019772986045615438,
      "loss": 0.9194,
      "step": 105
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019768200297248193,
      "loss": 0.8592,
      "step": 106
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001976336522016893,
      "loss": 0.856,
      "step": 107
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019758480838794453,
      "loss": 0.8841,
      "step": 108
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001975354717779053,
      "loss": 0.8962,
      "step": 109
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000197485642620718,
      "loss": 0.8415,
      "step": 110
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019743532116801624,
      "loss": 0.8843,
      "step": 111
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001973845076739198,
      "loss": 0.8918,
      "step": 112
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019733320239503322,
      "loss": 0.836,
      "step": 113
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019728140559044445,
      "loss": 0.8442,
      "step": 114
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019722911752172363,
      "loss": 0.8471,
      "step": 115
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019717633845292175,
      "loss": 0.8407,
      "step": 116
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019712306865056936,
      "loss": 0.8982,
      "step": 117
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019706930838367517,
      "loss": 0.8233,
      "step": 118
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001970150579237246,
      "loss": 0.8739,
      "step": 119
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001969603175446787,
      "loss": 0.8956,
      "step": 120
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019690508752297234,
      "loss": 0.8368,
      "step": 121
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019684936813751326,
      "loss": 0.8628,
      "step": 122
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019679315966968035,
      "loss": 0.8485,
      "step": 123
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019673646240332232,
      "loss": 0.8465,
      "step": 124
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019667927662475636,
      "loss": 0.8258,
      "step": 125
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001966216026227665,
      "loss": 0.8668,
      "step": 126
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019656344068860233,
      "loss": 0.8556,
      "step": 127
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019650479111597748,
      "loss": 0.8997,
      "step": 128
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019644565420106805,
      "loss": 0.8958,
      "step": 129
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001963860302425113,
      "loss": 0.8866,
      "step": 130
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019632591954140387,
      "loss": 0.8723,
      "step": 131
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019626532240130055,
      "loss": 0.8614,
      "step": 132
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019620423912821252,
      "loss": 0.8564,
      "step": 133
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019614267003060593,
      "loss": 0.8998,
      "step": 134
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019608061541940037,
      "loss": 0.8743,
      "step": 135
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019601807560796713,
      "loss": 0.8084,
      "step": 136
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019595505091212783,
      "loss": 0.8503,
      "step": 137
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001958915416501526,
      "loss": 0.8093,
      "step": 138
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019582754814275873,
      "loss": 0.8413,
      "step": 139
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019576307071310882,
      "loss": 0.9218,
      "step": 140
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019569810968680926,
      "loss": 0.8248,
      "step": 141
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019563266539190862,
      "loss": 0.8592,
      "step": 142
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019556673815889587,
      "loss": 0.8835,
      "step": 143
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019550032832069882,
      "loss": 0.8353,
      "step": 144
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019543343621268244,
      "loss": 0.8212,
      "step": 145
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000195366062172647,
      "loss": 0.8606,
      "step": 146
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019529820654082665,
      "loss": 0.8585,
      "step": 147
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019522986965988745,
      "loss": 0.9144,
      "step": 148
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019516105187492575,
      "loss": 0.9081,
      "step": 149
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019509175353346644,
      "loss": 0.823,
      "step": 150
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001950219749854612,
      "loss": 0.8732,
      "step": 151
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019495171658328664,
      "loss": 0.8625,
      "step": 152
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019488097868174275,
      "loss": 0.8403,
      "step": 153
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019480976163805078,
      "loss": 0.8427,
      "step": 154
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019473806581185175,
      "loss": 0.8417,
      "step": 155
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019466589156520448,
      "loss": 0.8334,
      "step": 156
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019459323926258366,
      "loss": 0.8514,
      "step": 157
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019452010927087826,
      "loss": 0.7686,
      "step": 158
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019444650195938953,
      "loss": 0.8638,
      "step": 159
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019437241769982907,
      "loss": 0.8867,
      "step": 160
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019429785686631714,
      "loss": 0.8116,
      "step": 161
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019422281983538054,
      "loss": 0.8035,
      "step": 162
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000194147306985951,
      "loss": 0.8244,
      "step": 163
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001940713186993629,
      "loss": 0.8609,
      "step": 164
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019399485535935172,
      "loss": 0.8357,
      "step": 165
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019391791735205182,
      "loss": 0.8386,
      "step": 166
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019384050506599462,
      "loss": 0.8402,
      "step": 167
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019376261889210664,
      "loss": 0.8348,
      "step": 168
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019368425922370748,
      "loss": 0.8332,
      "step": 169
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019360542645650784,
      "loss": 0.8906,
      "step": 170
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019352612098860755,
      "loss": 0.7958,
      "step": 171
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019344634322049356,
      "loss": 0.8493,
      "step": 172
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019336609355503787,
      "loss": 0.8244,
      "step": 173
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019328537239749553,
      "loss": 0.8464,
      "step": 174
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019320418015550265,
      "loss": 0.8518,
      "step": 175
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019312251723907422,
      "loss": 0.8635,
      "step": 176
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.873156726360321,
      "eval_runtime": 58.1152,
      "eval_samples_per_second": 6.883,
      "eval_steps_per_second": 3.441,
      "step": 176
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001930403840606021,
      "loss": 0.9014,
      "step": 177
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019295778103485298,
      "loss": 0.8353,
      "step": 178
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019287470857896622,
      "loss": 0.8487,
      "step": 179
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019279116711245177,
      "loss": 0.8616,
      "step": 180
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019270715705718808,
      "loss": 0.8197,
      "step": 181
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019262267883741986,
      "loss": 0.8525,
      "step": 182
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001925377328797561,
      "loss": 0.8649,
      "step": 183
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019245231961316782,
      "loss": 0.8416,
      "step": 184
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019236643946898588,
      "loss": 0.8973,
      "step": 185
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019228009288089885,
      "loss": 0.7733,
      "step": 186
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019219328028495083,
      "loss": 0.8239,
      "step": 187
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019210600211953918,
      "loss": 0.7993,
      "step": 188
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019201825882541245,
      "loss": 0.8195,
      "step": 189
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019193005084566797,
      "loss": 0.7977,
      "step": 190
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019184137862574973,
      "loss": 0.85,
      "step": 191
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019175224261344602,
      "loss": 0.8245,
      "step": 192
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019166264325888742,
      "loss": 0.8929,
      "step": 193
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019157258101454416,
      "loss": 0.8194,
      "step": 194
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019148205633522414,
      "loss": 0.8493,
      "step": 195
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019139106967807062,
      "loss": 0.8489,
      "step": 196
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019129962150255957,
      "loss": 0.862,
      "step": 197
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019120771227049778,
      "loss": 0.8723,
      "step": 198
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019111534244602033,
      "loss": 0.8193,
      "step": 199
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019102251249558812,
      "loss": 0.8619,
      "step": 200
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019092922288798585,
      "loss": 0.8299,
      "step": 201
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001908354740943193,
      "loss": 0.8403,
      "step": 202
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001907412665880132,
      "loss": 0.8623,
      "step": 203
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019064660084480868,
      "loss": 0.8998,
      "step": 204
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019055147734276098,
      "loss": 0.8595,
      "step": 205
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019045589656223696,
      "loss": 0.8264,
      "step": 206
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019035985898591275,
      "loss": 0.8368,
      "step": 207
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001902633650987712,
      "loss": 0.8436,
      "step": 208
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019016641538809954,
      "loss": 0.8625,
      "step": 209
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019006901034348688,
      "loss": 0.8775,
      "step": 210
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001899711504568217,
      "loss": 0.7985,
      "step": 211
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018987283622228944,
      "loss": 0.8656,
      "step": 212
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018977406813636992,
      "loss": 0.8672,
      "step": 213
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018967484669783492,
      "loss": 0.8057,
      "step": 214
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001895751724077456,
      "loss": 0.8596,
      "step": 215
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018947504576944998,
      "loss": 0.8373,
      "step": 216
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001893744672885804,
      "loss": 0.8559,
      "step": 217
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000189273437473051,
      "loss": 0.7931,
      "step": 218
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018917195683305517,
      "loss": 0.8594,
      "step": 219
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018907002588106276,
      "loss": 0.877,
      "step": 220
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018896764513181785,
      "loss": 0.8297,
      "step": 221
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001888648151023359,
      "loss": 0.8407,
      "step": 222
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018876153631190116,
      "loss": 0.8597,
      "step": 223
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018865780928206417,
      "loss": 0.8647,
      "step": 224
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018855363453663894,
      "loss": 0.8075,
      "step": 225
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001884490126017005,
      "loss": 0.8438,
      "step": 226
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018834394400558217,
      "loss": 0.8274,
      "step": 227
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001882384292788728,
      "loss": 0.8721,
      "step": 228
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001881324689544142,
      "loss": 0.8204,
      "step": 229
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018802606356729844,
      "loss": 0.8424,
      "step": 230
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001879192136548651,
      "loss": 0.8044,
      "step": 231
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018781191975669859,
      "loss": 0.8082,
      "step": 232
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001877041824146254,
      "loss": 0.8438,
      "step": 233
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001875960021727114,
      "loss": 0.8748,
      "step": 234
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018748737957725904,
      "loss": 0.854,
      "step": 235
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001873783151768047,
      "loss": 0.851,
      "step": 236
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00018726880952211575,
      "loss": 0.8547,
      "step": 237
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001871588631661879,
      "loss": 0.8399,
      "step": 238
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001870484766642424,
      "loss": 0.8749,
      "step": 239
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00018693765057372318,
      "loss": 0.8127,
      "step": 240
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00018682638545429407,
      "loss": 0.8481,
      "step": 241
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00018671468186783592,
      "loss": 0.8164,
      "step": 242
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.8275,
      "step": 243
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001864899615524244,
      "loss": 0.799,
      "step": 244
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018637694595829252,
      "loss": 0.7889,
      "step": 245
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001862634941667689,
      "loss": 0.8524,
      "step": 246
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018614960675077696,
      "loss": 0.8409,
      "step": 247
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018603528428544,
      "loss": 0.7696,
      "step": 248
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018592052734807825,
      "loss": 0.8262,
      "step": 249
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018580533651820603,
      "loss": 0.8208,
      "step": 250
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018568971237752882,
      "loss": 0.8284,
      "step": 251
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018557365550994024,
      "loss": 0.8471,
      "step": 252
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018545716650151915,
      "loss": 0.8417,
      "step": 253
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001853402459405267,
      "loss": 0.8051,
      "step": 254
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018522289441740334,
      "loss": 0.8433,
      "step": 255
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018510511252476587,
      "loss": 0.8526,
      "step": 256
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018498690085740445,
      "loss": 0.805,
      "step": 257
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018486826001227948,
      "loss": 0.8524,
      "step": 258
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018474919058851877,
      "loss": 0.8487,
      "step": 259
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018462969318741433,
      "loss": 0.8604,
      "step": 260
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018450976841241951,
      "loss": 0.8518,
      "step": 261
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001843894168691459,
      "loss": 0.769,
      "step": 262
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001842686391653601,
      "loss": 0.8178,
      "step": 263
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018414743591098085,
      "loss": 0.8224,
      "step": 264
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018402580771807595,
      "loss": 0.8227,
      "step": 265
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018390375520085903,
      "loss": 0.8333,
      "step": 266
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018378127897568662,
      "loss": 0.8207,
      "step": 267
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018365837966105483,
      "loss": 0.8144,
      "step": 268
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018353505787759643,
      "loss": 0.8289,
      "step": 269
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001834113142480776,
      "loss": 0.8387,
      "step": 270
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018328714939739476,
      "loss": 0.8306,
      "step": 271
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018316256395257155,
      "loss": 0.8485,
      "step": 272
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018303755854275555,
      "loss": 0.7812,
      "step": 273
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018291213379921512,
      "loss": 0.7986,
      "step": 274
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018278629035533623,
      "loss": 0.8012,
      "step": 275
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018266002884661928,
      "loss": 0.8854,
      "step": 276
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018253334991067581,
      "loss": 0.8528,
      "step": 277
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018240625418722541,
      "loss": 0.8012,
      "step": 278
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018227874231809238,
      "loss": 0.8785,
      "step": 279
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018215081494720248,
      "loss": 0.8013,
      "step": 280
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018202247272057983,
      "loss": 0.7962,
      "step": 281
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018189371628634347,
      "loss": 0.8746,
      "step": 282
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018176454629470414,
      "loss": 0.8755,
      "step": 283
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001816349633979611,
      "loss": 0.8665,
      "step": 284
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018150496825049866,
      "loss": 0.8163,
      "step": 285
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018137456150878303,
      "loss": 0.8478,
      "step": 286
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001812437438313589,
      "loss": 0.7785,
      "step": 287
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018111251587884616,
      "loss": 0.7899,
      "step": 288
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018098087831393663,
      "loss": 0.8274,
      "step": 289
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018084883180139052,
      "loss": 0.8124,
      "step": 290
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018071637700803334,
      "loss": 0.8438,
      "step": 291
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001805835146027522,
      "loss": 0.8542,
      "step": 292
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00018045024525649284,
      "loss": 0.8308,
      "step": 293
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00018031656964225584,
      "loss": 0.8677,
      "step": 294
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00018018248843509354,
      "loss": 0.8398,
      "step": 295
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00018004800231210638,
      "loss": 0.8078,
      "step": 296
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001799131119524397,
      "loss": 0.7889,
      "step": 297
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001797778180372801,
      "loss": 0.8287,
      "step": 298
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017964212124985224,
      "loss": 0.8584,
      "step": 299
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001795060222754151,
      "loss": 0.8178,
      "step": 300
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001793695218012588,
      "loss": 0.8409,
      "step": 301
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000179232620516701,
      "loss": 0.8806,
      "step": 302
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017909531911308325,
      "loss": 0.8563,
      "step": 303
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017895761828376795,
      "loss": 0.8051,
      "step": 304
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017881951872413435,
      "loss": 0.8475,
      "step": 305
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017868102113157534,
      "loss": 0.804,
      "step": 306
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001785421262054939,
      "loss": 0.8033,
      "step": 307
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001784028346472994,
      "loss": 0.8219,
      "step": 308
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017826314716040423,
      "loss": 0.8595,
      "step": 309
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017812306445022025,
      "loss": 0.8405,
      "step": 310
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017798258722415508,
      "loss": 0.7675,
      "step": 311
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001778417161916087,
      "loss": 0.8026,
      "step": 312
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017770045206396963,
      "loss": 0.8292,
      "step": 313
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001775587955546117,
      "loss": 0.8287,
      "step": 314
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001774167473788901,
      "loss": 0.8299,
      "step": 315
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017727430825413792,
      "loss": 0.8101,
      "step": 316
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017713147889966262,
      "loss": 0.7898,
      "step": 317
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001769882600367421,
      "loss": 0.8084,
      "step": 318
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017684465238862148,
      "loss": 0.8087,
      "step": 319
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000176700656680509,
      "loss": 0.8065,
      "step": 320
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017655627363957277,
      "loss": 0.8368,
      "step": 321
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001764115039949367,
      "loss": 0.8231,
      "step": 322
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001762663484776772,
      "loss": 0.8333,
      "step": 323
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017612080782081923,
      "loss": 0.8453,
      "step": 324
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017597488275933267,
      "loss": 0.8669,
      "step": 325
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017582857403012866,
      "loss": 0.8022,
      "step": 326
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017568188237205575,
      "loss": 0.8116,
      "step": 327
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017553480852589636,
      "loss": 0.8307,
      "step": 328
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017538735323436284,
      "loss": 0.7986,
      "step": 329
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017523951724209388,
      "loss": 0.8278,
      "step": 330
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017509130129565067,
      "loss": 0.8397,
      "step": 331
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001749427061435131,
      "loss": 0.7862,
      "step": 332
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017479373253607606,
      "loss": 0.8574,
      "step": 333
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017464438122564556,
      "loss": 0.8312,
      "step": 334
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001744946529664351,
      "loss": 0.8666,
      "step": 335
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017434454851456162,
      "loss": 0.8027,
      "step": 336
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017419406862804183,
      "loss": 0.8962,
      "step": 337
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017404321406678844,
      "loss": 0.8286,
      "step": 338
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017389198559260614,
      "loss": 0.8167,
      "step": 339
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017374038396918788,
      "loss": 0.831,
      "step": 340
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017358840996211104,
      "loss": 0.8218,
      "step": 341
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017343606433883348,
      "loss": 0.7902,
      "step": 342
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017328334786868968,
      "loss": 0.8418,
      "step": 343
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017313026132288682,
      "loss": 0.853,
      "step": 344
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017297680547450107,
      "loss": 0.8153,
      "step": 345
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017282298109847345,
      "loss": 0.8121,
      "step": 346
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017266878897160605,
      "loss": 0.8085,
      "step": 347
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017251422987255802,
      "loss": 0.8342,
      "step": 348
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001723593045818418,
      "loss": 0.7986,
      "step": 349
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017220401388181903,
      "loss": 0.7917,
      "step": 350
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017204835855669657,
      "loss": 0.8111,
      "step": 351
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017189233939252267,
      "loss": 0.8284,
      "step": 352
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.846347987651825,
      "eval_runtime": 58.037,
      "eval_samples_per_second": 6.892,
      "eval_steps_per_second": 3.446,
      "step": 352
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017173595717718295,
      "loss": 0.8536,
      "step": 353
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017157921270039646,
      "loss": 0.8388,
      "step": 354
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001714221067537115,
      "loss": 0.7963,
      "step": 355
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017126464013050185,
      "loss": 0.7786,
      "step": 356
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017110681362596272,
      "loss": 0.8085,
      "step": 357
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017094862803710664,
      "loss": 0.8535,
      "step": 358
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017079008416275954,
      "loss": 0.8492,
      "step": 359
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017063118280355655,
      "loss": 0.884,
      "step": 360
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017047192476193825,
      "loss": 0.8504,
      "step": 361
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001703123108421463,
      "loss": 0.8377,
      "step": 362
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00017015234185021957,
      "loss": 0.8179,
      "step": 363
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016999201859399,
      "loss": 0.8584,
      "step": 364
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016983134188307858,
      "loss": 0.8151,
      "step": 365
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001696703125288912,
      "loss": 0.7949,
      "step": 366
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001695089313446145,
      "loss": 0.7939,
      "step": 367
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000169347199145212,
      "loss": 0.8024,
      "step": 368
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016918511674741965,
      "loss": 0.8164,
      "step": 369
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016902268496974201,
      "loss": 0.8424,
      "step": 370
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016885990463244785,
      "loss": 0.8081,
      "step": 371
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001686967765575663,
      "loss": 0.8728,
      "step": 372
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001685333015688824,
      "loss": 0.8443,
      "step": 373
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016836948049193316,
      "loss": 0.7933,
      "step": 374
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016820531415400334,
      "loss": 0.8349,
      "step": 375
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016804080338412108,
      "loss": 0.864,
      "step": 376
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016787594901305404,
      "loss": 0.8422,
      "step": 377
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000167710751873305,
      "loss": 0.7993,
      "step": 378
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001675452127991077,
      "loss": 0.8051,
      "step": 379
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016737933262642258,
      "loss": 0.7417,
      "step": 380
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001672131121929326,
      "loss": 0.7987,
      "step": 381
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016704655233803912,
      "loss": 0.8387,
      "step": 382
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016687965390285747,
      "loss": 0.815,
      "step": 383
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016671241773021276,
      "loss": 0.8293,
      "step": 384
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001665448446646357,
      "loss": 0.7945,
      "step": 385
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016637693555235825,
      "loss": 0.801,
      "step": 386
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016620869124130944,
      "loss": 0.8003,
      "step": 387
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000166040112581111,
      "loss": 0.8379,
      "step": 388
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016587120042307305,
      "loss": 0.7929,
      "step": 389
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016570195562018992,
      "loss": 0.7693,
      "step": 390
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016553237902713574,
      "loss": 0.8191,
      "step": 391
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016536247150026017,
      "loss": 0.826,
      "step": 392
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000165192233897584,
      "loss": 0.814,
      "step": 393
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016502166707879504,
      "loss": 0.8159,
      "step": 394
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016485077190524341,
      "loss": 0.8702,
      "step": 395
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016467954923993756,
      "loss": 0.8188,
      "step": 396
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016450799994753966,
      "loss": 0.8238,
      "step": 397
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016433612489436135,
      "loss": 0.8168,
      "step": 398
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016416392494835935,
      "loss": 0.7938,
      "step": 399
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016399140097913105,
      "loss": 0.8115,
      "step": 400
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016381855385791015,
      "loss": 0.8096,
      "step": 401
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016364538445756224,
      "loss": 0.7986,
      "step": 402
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016347189365258034,
      "loss": 0.7957,
      "step": 403
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001632980823190807,
      "loss": 0.8502,
      "step": 404
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000163123951334798,
      "loss": 0.8214,
      "step": 405
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016294950157908132,
      "loss": 0.8192,
      "step": 406
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016277473393288937,
      "loss": 0.8425,
      "step": 407
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016259964927878626,
      "loss": 0.7956,
      "step": 408
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000162424248500937,
      "loss": 0.7574,
      "step": 409
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001622485324851029,
      "loss": 0.8459,
      "step": 410
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016207250211863728,
      "loss": 0.7867,
      "step": 411
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016189615829048095,
      "loss": 0.8068,
      "step": 412
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016171950189115751,
      "loss": 0.8387,
      "step": 413
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001615425338127692,
      "loss": 0.7998,
      "step": 414
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016136525494899208,
      "loss": 0.819,
      "step": 415
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016118766619507176,
      "loss": 0.8168,
      "step": 416
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016100976844781877,
      "loss": 0.801,
      "step": 417
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016083156260560387,
      "loss": 0.8251,
      "step": 418
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016065304956835395,
      "loss": 0.8453,
      "step": 419
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016047423023754696,
      "loss": 0.8419,
      "step": 420
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016029510551620777,
      "loss": 0.7758,
      "step": 421
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016011567630890336,
      "loss": 0.8178,
      "step": 422
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001599359435217384,
      "loss": 0.8313,
      "step": 423
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00015975590806235058,
      "loss": 0.8286,
      "step": 424
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001595755708399061,
      "loss": 0.8054,
      "step": 425
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000159394932765095,
      "loss": 0.834,
      "step": 426
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015921399475012663,
      "loss": 0.8343,
      "step": 427
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000159032757708725,
      "loss": 0.813,
      "step": 428
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015885122255612425,
      "loss": 0.7911,
      "step": 429
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015866939020906377,
      "loss": 0.8037,
      "step": 430
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015848726158578403,
      "loss": 0.838,
      "step": 431
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001583048376060215,
      "loss": 0.8053,
      "step": 432
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015812211919100411,
      "loss": 0.8014,
      "step": 433
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015793910726344694,
      "loss": 0.7935,
      "step": 434
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015775580274754697,
      "loss": 0.7803,
      "step": 435
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015757220656897896,
      "loss": 0.8563,
      "step": 436
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015738831965489048,
      "loss": 0.7825,
      "step": 437
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001572041429338972,
      "loss": 0.8035,
      "step": 438
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015701967733607844,
      "loss": 0.8199,
      "step": 439
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015683492379297222,
      "loss": 0.8314,
      "step": 440
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015664988323757072,
      "loss": 0.7746,
      "step": 441
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015646455660431552,
      "loss": 0.7724,
      "step": 442
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001562789448290928,
      "loss": 0.8263,
      "step": 443
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015609304884922878,
      "loss": 0.7956,
      "step": 444
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001559068696034848,
      "loss": 0.8388,
      "step": 445
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015572040803205273,
      "loss": 0.8226,
      "step": 446
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001555336650765502,
      "loss": 0.8014,
      "step": 447
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015534664168001568,
      "loss": 0.8371,
      "step": 448
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000155159338786904,
      "loss": 0.8162,
      "step": 449
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015497175734308135,
      "loss": 0.8334,
      "step": 450
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015478389829582057,
      "loss": 0.802,
      "step": 451
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015459576259379637,
      "loss": 0.8153,
      "step": 452
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015440735118708062,
      "loss": 0.8418,
      "step": 453
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001542186650271374,
      "loss": 0.7649,
      "step": 454
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015402970506681832,
      "loss": 0.8178,
      "step": 455
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001538404722603577,
      "loss": 0.7929,
      "step": 456
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015365096756336756,
      "loss": 0.7714,
      "step": 457
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015346119193283313,
      "loss": 0.7547,
      "step": 458
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001532711463271077,
      "loss": 0.8495,
      "step": 459
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000153080831705908,
      "loss": 0.8482,
      "step": 460
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015289024903030924,
      "loss": 0.7974,
      "step": 461
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015269939926274028,
      "loss": 0.8091,
      "step": 462
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015250828336697876,
      "loss": 0.771,
      "step": 463
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015231690230814633,
      "loss": 0.8292,
      "step": 464
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015212525705270356,
      "loss": 0.8259,
      "step": 465
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015193334856844528,
      "loss": 0.8219,
      "step": 466
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015174117782449563,
      "loss": 0.8284,
      "step": 467
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015154874579130308,
      "loss": 0.8191,
      "step": 468
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001513560534406356,
      "loss": 0.8275,
      "step": 469
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001511631017455758,
      "loss": 0.7894,
      "step": 470
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015096989168051595,
      "loss": 0.8161,
      "step": 471
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015077642422115295,
      "loss": 0.8246,
      "step": 472
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001505827003444837,
      "loss": 0.8306,
      "step": 473
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015038872102879981,
      "loss": 0.7859,
      "step": 474
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015019448725368305,
      "loss": 0.7873,
      "step": 475
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.812,
      "step": 476
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00014980526024989738,
      "loss": 0.8562,
      "step": 477
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00014961026898679703,
      "loss": 0.8009,
      "step": 478
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001494150271953908,
      "loss": 0.8271,
      "step": 479
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00014921953586163577,
      "loss": 0.8172,
      "step": 480
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001490237959727492,
      "loss": 0.7966,
      "step": 481
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00014882780851720344,
      "loss": 0.8242,
      "step": 482
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014863157448472122,
      "loss": 0.7957,
      "step": 483
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001484350948662703,
      "loss": 0.8224,
      "step": 484
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014823837065405863,
      "loss": 0.784,
      "step": 485
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001480414028415295,
      "loss": 0.8139,
      "step": 486
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014784419242335614,
      "loss": 0.7678,
      "step": 487
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014764674039543718,
      "loss": 0.772,
      "step": 488
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014744904775489107,
      "loss": 0.8111,
      "step": 489
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001472511155000516,
      "loss": 0.8256,
      "step": 490
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00014705294463046248,
      "loss": 0.8292,
      "step": 491
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00014685453614687231,
      "loss": 0.7988,
      "step": 492
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001466558910512298,
      "loss": 0.7818,
      "step": 493
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00014645701034667847,
      "loss": 0.8344,
      "step": 494
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001462578950375516,
      "loss": 0.8063,
      "step": 495
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00014605854612936728,
      "loss": 0.7822,
      "step": 496
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014585896462882317,
      "loss": 0.8224,
      "step": 497
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014565915154379162,
      "loss": 0.8074,
      "step": 498
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014545910788331433,
      "loss": 0.7734,
      "step": 499
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001452588346575975,
      "loss": 0.7801,
      "step": 500
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014505833287800662,
      "loss": 0.8452,
      "step": 501
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014485760355706123,
      "loss": 0.7961,
      "step": 502
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014465664770843008,
      "loss": 0.8104,
      "step": 503
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014445546634692582,
      "loss": 0.8137,
      "step": 504
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001442540604884999,
      "loss": 0.7949,
      "step": 505
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014405243115023748,
      "loss": 0.7968,
      "step": 506
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014385057935035228,
      "loss": 0.7942,
      "step": 507
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014364850610818145,
      "loss": 0.7847,
      "step": 508
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001434462124441804,
      "loss": 0.7803,
      "step": 509
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014324369937991765,
      "loss": 0.9007,
      "step": 510
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00014304096793806958,
      "loss": 0.8213,
      "step": 511
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001428380191424156,
      "loss": 0.8121,
      "step": 512
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00014263485401783252,
      "loss": 0.7978,
      "step": 513
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00014243147359028967,
      "loss": 0.8319,
      "step": 514
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00014222787888684363,
      "loss": 0.7793,
      "step": 515
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001420240709356331,
      "loss": 0.7744,
      "step": 516
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00014182005076587365,
      "loss": 0.769,
      "step": 517
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00014161581940785252,
      "loss": 0.8161,
      "step": 518
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001414113778929234,
      "loss": 0.7841,
      "step": 519
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00014120672725350137,
      "loss": 0.7876,
      "step": 520
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00014100186852305743,
      "loss": 0.7723,
      "step": 521
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00014079680273611358,
      "loss": 0.8469,
      "step": 522
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001405915309282373,
      "loss": 0.754,
      "step": 523
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00014038605413603652,
      "loss": 0.8394,
      "step": 524
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00014018037339715437,
      "loss": 0.813,
      "step": 525
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00013997448975026382,
      "loss": 0.7784,
      "step": 526
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00013976840423506257,
      "loss": 0.8189,
      "step": 527
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001395621178922677,
      "loss": 0.7928,
      "step": 528
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.8294777870178223,
      "eval_runtime": 58.0411,
      "eval_samples_per_second": 6.892,
      "eval_steps_per_second": 3.446,
      "step": 528
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00013935563176361042,
      "loss": 0.7904,
      "step": 529
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00013914894689183097,
      "loss": 0.7809,
      "step": 530
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00013894206432067308,
      "loss": 0.7594,
      "step": 531
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00013873498509487902,
      "loss": 0.8133,
      "step": 532
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000138527710260184,
      "loss": 0.7861,
      "step": 533
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00013832024086331103,
      "loss": 0.798,
      "step": 534
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001381125779519658,
      "loss": 0.8223,
      "step": 535
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00013790472257483108,
      "loss": 0.7924,
      "step": 536
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00013769667578156165,
      "loss": 0.8164,
      "step": 537
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00013748843862277898,
      "loss": 0.8427,
      "step": 538
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00013728001215006574,
      "loss": 0.8305,
      "step": 539
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001370713974159607,
      "loss": 0.805,
      "step": 540
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001368625954739534,
      "loss": 0.7933,
      "step": 541
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00013665360737847857,
      "loss": 0.8358,
      "step": 542
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00013644443418491125,
      "loss": 0.813,
      "step": 543
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00013623507694956102,
      "loss": 0.7695,
      "step": 544
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001360255367296669,
      "loss": 0.825,
      "step": 545
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00013581581458339207,
      "loss": 0.7928,
      "step": 546
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00013560591156981831,
      "loss": 0.8634,
      "step": 547
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00013539582874894083,
      "loss": 0.7986,
      "step": 548
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00013518556718166282,
      "loss": 0.8162,
      "step": 549
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00013497512792979012,
      "loss": 0.8048,
      "step": 550
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001347645120560259,
      "loss": 0.8305,
      "step": 551
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00013455372062396524,
      "loss": 0.7757,
      "step": 552
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013434275469808974,
      "loss": 0.8034,
      "step": 553
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001341316153437623,
      "loss": 0.8023,
      "step": 554
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001339203036272215,
      "loss": 0.8447,
      "step": 555
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013370882061557635,
      "loss": 0.8172,
      "step": 556
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013349716737680092,
      "loss": 0.8713,
      "step": 557
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013328534497972894,
      "loss": 0.7882,
      "step": 558
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013307335449404836,
      "loss": 0.812,
      "step": 559
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001328611969902959,
      "loss": 0.8051,
      "step": 560
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013264887353985175,
      "loss": 0.7853,
      "step": 561
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013243638521493424,
      "loss": 0.8625,
      "step": 562
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013222373308859406,
      "loss": 0.7404,
      "step": 563
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013201091823470936,
      "loss": 0.7813,
      "step": 564
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013179794172797976,
      "loss": 0.7803,
      "step": 565
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013158480464392144,
      "loss": 0.8549,
      "step": 566
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00013137150805886147,
      "loss": 0.7503,
      "step": 567
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001311580530499322,
      "loss": 0.8602,
      "step": 568
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001309444406950663,
      "loss": 0.8061,
      "step": 569
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00013073067207299073,
      "loss": 0.8279,
      "step": 570
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00013051674826322176,
      "loss": 0.7735,
      "step": 571
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001303026703460594,
      "loss": 0.7717,
      "step": 572
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00013008843940258164,
      "loss": 0.7514,
      "step": 573
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00012987405651463952,
      "loss": 0.7604,
      "step": 574
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00012965952276485128,
      "loss": 0.7884,
      "step": 575
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00012944483923659693,
      "loss": 0.8118,
      "step": 576
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00012923000701401297,
      "loss": 0.8253,
      "step": 577
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00012901502718198663,
      "loss": 0.7794,
      "step": 578
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001287999008261508,
      "loss": 0.8049,
      "step": 579
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00012858462903287814,
      "loss": 0.8225,
      "step": 580
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012836921288927574,
      "loss": 0.7848,
      "step": 581
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012815365348317975,
      "loss": 0.8081,
      "step": 582
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012793795190314973,
      "loss": 0.7644,
      "step": 583
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012772210923846317,
      "loss": 0.8084,
      "step": 584
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012750612657911012,
      "loss": 0.7859,
      "step": 585
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001272900050157875,
      "loss": 0.8209,
      "step": 586
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012707374563989375,
      "loss": 0.8092,
      "step": 587
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012685734954352327,
      "loss": 0.8402,
      "step": 588
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001266408178194608,
      "loss": 0.7294,
      "step": 589
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012642415156117605,
      "loss": 0.8243,
      "step": 590
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001262073518628181,
      "loss": 0.8151,
      "step": 591
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012599041981920995,
      "loss": 0.7833,
      "step": 592
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012577335652584284,
      "loss": 0.8321,
      "step": 593
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012555616307887086,
      "loss": 0.7716,
      "step": 594
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012533884057510538,
      "loss": 0.7746,
      "step": 595
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012512139011200947,
      "loss": 0.8502,
      "step": 596
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012490381278769242,
      "loss": 0.8417,
      "step": 597
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012468610970090411,
      "loss": 0.8002,
      "step": 598
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012446828195102956,
      "loss": 0.762,
      "step": 599
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012425033063808328,
      "loss": 0.8302,
      "step": 600
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012403225686270384,
      "loss": 0.8135,
      "step": 601
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00012381406172614812,
      "loss": 0.7791,
      "step": 602
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000123595746330286,
      "loss": 0.7753,
      "step": 603
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001233773117775946,
      "loss": 0.7365,
      "step": 604
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001231587591711527,
      "loss": 0.8144,
      "step": 605
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00012294008961463539,
      "loss": 0.7906,
      "step": 606
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00012272130421230818,
      "loss": 0.8327,
      "step": 607
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001225024040690218,
      "loss": 0.7626,
      "step": 608
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012228339029020624,
      "loss": 0.8493,
      "step": 609
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012206426398186534,
      "loss": 0.7778,
      "step": 610
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012184502625057139,
      "loss": 0.805,
      "step": 611
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012162567820345912,
      "loss": 0.8099,
      "step": 612
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012140622094822054,
      "loss": 0.7626,
      "step": 613
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012118665559309906,
      "loss": 0.8807,
      "step": 614
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012096698324688392,
      "loss": 0.8007,
      "step": 615
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00012074720501890484,
      "loss": 0.7872,
      "step": 616
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00012052732201902608,
      "loss": 0.7814,
      "step": 617
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00012030733535764107,
      "loss": 0.8192,
      "step": 618
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001200872461456667,
      "loss": 0.8097,
      "step": 619
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001198670554945377,
      "loss": 0.7605,
      "step": 620
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00011964676451620112,
      "loss": 0.817,
      "step": 621
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00011942637432311059,
      "loss": 0.8013,
      "step": 622
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00011920588602822083,
      "loss": 0.7394,
      "step": 623
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011898530074498194,
      "loss": 0.8615,
      "step": 624
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011876461958733381,
      "loss": 0.745,
      "step": 625
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011854384366970046,
      "loss": 0.8218,
      "step": 626
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011832297410698447,
      "loss": 0.776,
      "step": 627
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011810201201456134,
      "loss": 0.781,
      "step": 628
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011788095850827381,
      "loss": 0.7886,
      "step": 629
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011765981470442624,
      "loss": 0.7804,
      "step": 630
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011743858171977899,
      "loss": 0.7484,
      "step": 631
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011721726067154282,
      "loss": 0.7553,
      "step": 632
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011699585267737317,
      "loss": 0.8006,
      "step": 633
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011677435885536452,
      "loss": 0.7649,
      "step": 634
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011655278032404489,
      "loss": 0.7723,
      "step": 635
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011633111820236991,
      "loss": 0.8024,
      "step": 636
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011610937360971747,
      "loss": 0.7931,
      "step": 637
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011588754766588188,
      "loss": 0.847,
      "step": 638
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011566564149106822,
      "loss": 0.7786,
      "step": 639
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011544365620588688,
      "loss": 0.8177,
      "step": 640
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011522159293134758,
      "loss": 0.7655,
      "step": 641
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011499945278885395,
      "loss": 0.7785,
      "step": 642
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011477723690019788,
      "loss": 0.8031,
      "step": 643
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001145549463875536,
      "loss": 0.844,
      "step": 644
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011433258237347235,
      "loss": 0.7841,
      "step": 645
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011411014598087644,
      "loss": 0.8228,
      "step": 646
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011388763833305371,
      "loss": 0.8026,
      "step": 647
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011366506055365194,
      "loss": 0.8072,
      "step": 648
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011344241376667284,
      "loss": 0.8113,
      "step": 649
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011321969909646683,
      "loss": 0.8151,
      "step": 650
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011299691766772709,
      "loss": 0.8332,
      "step": 651
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011277407060548373,
      "loss": 0.7731,
      "step": 652
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011255115903509861,
      "loss": 0.8198,
      "step": 653
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011232818408225909,
      "loss": 0.7763,
      "step": 654
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001121051468729728,
      "loss": 0.8101,
      "step": 655
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011188204853356163,
      "loss": 0.7844,
      "step": 656
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011165889019065618,
      "loss": 0.8057,
      "step": 657
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001114356729711902,
      "loss": 0.7925,
      "step": 658
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011121239800239458,
      "loss": 0.7849,
      "step": 659
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011098906641179194,
      "loss": 0.811,
      "step": 660
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011076567932719088,
      "loss": 0.7957,
      "step": 661
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011054223787668008,
      "loss": 0.8227,
      "step": 662
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011031874318862294,
      "loss": 0.8388,
      "step": 663
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011009519639165162,
      "loss": 0.7837,
      "step": 664
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010987159861466143,
      "loss": 0.8168,
      "step": 665
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010964795098680512,
      "loss": 0.8015,
      "step": 666
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001094242546374872,
      "loss": 0.8834,
      "step": 667
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010920051069635822,
      "loss": 0.7445,
      "step": 668
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010897672029330906,
      "loss": 0.84,
      "step": 669
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010875288455846522,
      "loss": 0.8329,
      "step": 670
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010852900462218117,
      "loss": 0.8016,
      "step": 671
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001083050816150345,
      "loss": 0.7757,
      "step": 672
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001080811166678204,
      "loss": 0.7858,
      "step": 673
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001078571109115458,
      "loss": 0.7934,
      "step": 674
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010763306547742375,
      "loss": 0.8384,
      "step": 675
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001074089814968676,
      "loss": 0.7513,
      "step": 676
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010718486010148547,
      "loss": 0.8118,
      "step": 677
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010696070242307432,
      "loss": 0.7644,
      "step": 678
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010673650959361439,
      "loss": 0.7744,
      "step": 679
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010651228274526339,
      "loss": 0.8201,
      "step": 680
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010628802301035085,
      "loss": 0.8065,
      "step": 681
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010606373152137241,
      "loss": 0.851,
      "step": 682
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000105839409410984,
      "loss": 0.8175,
      "step": 683
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010561505781199618,
      "loss": 0.7985,
      "step": 684
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010539067785736856,
      "loss": 0.801,
      "step": 685
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010516627068020373,
      "loss": 0.8111,
      "step": 686
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010494183741374194,
      "loss": 0.8076,
      "step": 687
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001047173791913551,
      "loss": 0.7516,
      "step": 688
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010449289714654109,
      "loss": 0.7644,
      "step": 689
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010426839241291828,
      "loss": 0.8133,
      "step": 690
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010404386612421942,
      "loss": 0.8554,
      "step": 691
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001038193194142862,
      "loss": 0.8334,
      "step": 692
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010359475341706346,
      "loss": 0.8241,
      "step": 693
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010337016926659333,
      "loss": 0.8197,
      "step": 694
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001031455680970098,
      "loss": 0.8107,
      "step": 695
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010292095104253259,
      "loss": 0.798,
      "step": 696
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010269631923746176,
      "loss": 0.8339,
      "step": 697
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010247167381617191,
      "loss": 0.7761,
      "step": 698
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010224701591310625,
      "loss": 0.8617,
      "step": 699
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010202234666277115,
      "loss": 0.7663,
      "step": 700
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00010179766719973023,
      "loss": 0.7603,
      "step": 701
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00010157297865859865,
      "loss": 0.7736,
      "step": 702
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001013482821740375,
      "loss": 0.8078,
      "step": 703
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00010112357888074793,
      "loss": 0.8313,
      "step": 704
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8154956698417664,
      "eval_runtime": 58.0041,
      "eval_samples_per_second": 6.896,
      "eval_steps_per_second": 3.448,
      "step": 704
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00010089886991346546,
      "loss": 0.8305,
      "step": 705
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001006741564069543,
      "loss": 0.7897,
      "step": 706
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00010044943949600154,
      "loss": 0.7778,
      "step": 707
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00010022472031541152,
      "loss": 0.8418,
      "step": 708
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001,
      "loss": 0.7684,
      "step": 709
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.977527968458849e-05,
      "loss": 0.8186,
      "step": 710
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.95505605039985e-05,
      "loss": 0.7882,
      "step": 711
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.932584359304571e-05,
      "loss": 0.7512,
      "step": 712
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.910113008653456e-05,
      "loss": 0.7849,
      "step": 713
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.887642111925209e-05,
      "loss": 0.748,
      "step": 714
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.865171782596252e-05,
      "loss": 0.783,
      "step": 715
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.842702134140135e-05,
      "loss": 0.7535,
      "step": 716
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.820233280026978e-05,
      "loss": 0.7904,
      "step": 717
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.797765333722887e-05,
      "loss": 0.6682,
      "step": 718
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.775298408689376e-05,
      "loss": 0.6695,
      "step": 719
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.752832618382811e-05,
      "loss": 0.6499,
      "step": 720
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.730368076253825e-05,
      "loss": 0.6766,
      "step": 721
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.707904895746742e-05,
      "loss": 0.6829,
      "step": 722
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.685443190299021e-05,
      "loss": 0.6721,
      "step": 723
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.662983073340668e-05,
      "loss": 0.7087,
      "step": 724
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.640524658293659e-05,
      "loss": 0.6777,
      "step": 725
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.618068058571382e-05,
      "loss": 0.6979,
      "step": 726
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.595613387578059e-05,
      "loss": 0.7113,
      "step": 727
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.573160758708173e-05,
      "loss": 0.6589,
      "step": 728
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.550710285345892e-05,
      "loss": 0.6768,
      "step": 729
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.528262080864496e-05,
      "loss": 0.674,
      "step": 730
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.505816258625809e-05,
      "loss": 0.7443,
      "step": 731
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.483372931979627e-05,
      "loss": 0.7131,
      "step": 732
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.460932214263146e-05,
      "loss": 0.6695,
      "step": 733
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.438494218800383e-05,
      "loss": 0.7017,
      "step": 734
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.416059058901604e-05,
      "loss": 0.6611,
      "step": 735
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.393626847862763e-05,
      "loss": 0.6162,
      "step": 736
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.371197698964916e-05,
      "loss": 0.6558,
      "step": 737
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.348771725473662e-05,
      "loss": 0.6492,
      "step": 738
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.326349040638563e-05,
      "loss": 0.6634,
      "step": 739
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.303929757692571e-05,
      "loss": 0.7001,
      "step": 740
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.281513989851451e-05,
      "loss": 0.6548,
      "step": 741
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.25910185031324e-05,
      "loss": 0.6798,
      "step": 742
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.236693452257627e-05,
      "loss": 0.6797,
      "step": 743
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.214288908845423e-05,
      "loss": 0.6712,
      "step": 744
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.191888333217964e-05,
      "loss": 0.6858,
      "step": 745
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.16949183849655e-05,
      "loss": 0.6552,
      "step": 746
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.147099537781887e-05,
      "loss": 0.6846,
      "step": 747
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.12471154415348e-05,
      "loss": 0.6847,
      "step": 748
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.102327970669097e-05,
      "loss": 0.6576,
      "step": 749
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.079948930364183e-05,
      "loss": 0.6937,
      "step": 750
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.05757453625128e-05,
      "loss": 0.6627,
      "step": 751
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.035204901319492e-05,
      "loss": 0.6721,
      "step": 752
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.01284013853386e-05,
      "loss": 0.684,
      "step": 753
    },
    {
      "epoch": 1.05,
      "learning_rate": 8.99048036083484e-05,
      "loss": 0.7072,
      "step": 754
    },
    {
      "epoch": 1.05,
      "learning_rate": 8.968125681137707e-05,
      "loss": 0.6447,
      "step": 755
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.94577621233199e-05,
      "loss": 0.7046,
      "step": 756
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.923432067280914e-05,
      "loss": 0.6803,
      "step": 757
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.901093358820807e-05,
      "loss": 0.6804,
      "step": 758
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.878760199760545e-05,
      "loss": 0.6731,
      "step": 759
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.856432702880984e-05,
      "loss": 0.7135,
      "step": 760
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.834110980934381e-05,
      "loss": 0.6752,
      "step": 761
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.81179514664384e-05,
      "loss": 0.6991,
      "step": 762
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.789485312702723e-05,
      "loss": 0.6478,
      "step": 763
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.767181591774092e-05,
      "loss": 0.6842,
      "step": 764
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.744884096490143e-05,
      "loss": 0.7104,
      "step": 765
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.722592939451625e-05,
      "loss": 0.681,
      "step": 766
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.700308233227295e-05,
      "loss": 0.6834,
      "step": 767
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.678030090353318e-05,
      "loss": 0.6959,
      "step": 768
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.655758623332719e-05,
      "loss": 0.6618,
      "step": 769
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.633493944634812e-05,
      "loss": 0.6753,
      "step": 770
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.611236166694627e-05,
      "loss": 0.615,
      "step": 771
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.588985401912357e-05,
      "loss": 0.6437,
      "step": 772
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.566741762652767e-05,
      "loss": 0.6994,
      "step": 773
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.544505361244642e-05,
      "loss": 0.6767,
      "step": 774
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.522276309980216e-05,
      "loss": 0.6672,
      "step": 775
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.500054721114604e-05,
      "loss": 0.6175,
      "step": 776
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.477840706865245e-05,
      "loss": 0.6923,
      "step": 777
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.455634379411314e-05,
      "loss": 0.7069,
      "step": 778
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.433435850893179e-05,
      "loss": 0.6827,
      "step": 779
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.411245233411817e-05,
      "loss": 0.702,
      "step": 780
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.389062639028255e-05,
      "loss": 0.7059,
      "step": 781
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.366888179763011e-05,
      "loss": 0.6807,
      "step": 782
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.344721967595515e-05,
      "loss": 0.6767,
      "step": 783
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.322564114463551e-05,
      "loss": 0.69,
      "step": 784
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.300414732262688e-05,
      "loss": 0.6421,
      "step": 785
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.27827393284572e-05,
      "loss": 0.643,
      "step": 786
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.256141828022103e-05,
      "loss": 0.6736,
      "step": 787
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.23401852955738e-05,
      "loss": 0.6758,
      "step": 788
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.211904149172621e-05,
      "loss": 0.683,
      "step": 789
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.189798798543869e-05,
      "loss": 0.6802,
      "step": 790
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.167702589301551e-05,
      "loss": 0.6789,
      "step": 791
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.145615633029956e-05,
      "loss": 0.7107,
      "step": 792
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.123538041266622e-05,
      "loss": 0.6624,
      "step": 793
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.101469925501807e-05,
      "loss": 0.6987,
      "step": 794
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.079411397177921e-05,
      "loss": 0.7041,
      "step": 795
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.057362567688942e-05,
      "loss": 0.6882,
      "step": 796
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.035323548379892e-05,
      "loss": 0.6777,
      "step": 797
    },
    {
      "epoch": 1.12,
      "learning_rate": 8.013294450546232e-05,
      "loss": 0.6607,
      "step": 798
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.991275385433332e-05,
      "loss": 0.6786,
      "step": 799
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.969266464235897e-05,
      "loss": 0.6944,
      "step": 800
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.947267798097391e-05,
      "loss": 0.7004,
      "step": 801
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.925279498109519e-05,
      "loss": 0.6481,
      "step": 802
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.903301675311609e-05,
      "loss": 0.7059,
      "step": 803
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.881334440690101e-05,
      "loss": 0.652,
      "step": 804
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.859377905177947e-05,
      "loss": 0.6876,
      "step": 805
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.837432179654088e-05,
      "loss": 0.69,
      "step": 806
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.815497374942862e-05,
      "loss": 0.6599,
      "step": 807
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.793573601813467e-05,
      "loss": 0.6534,
      "step": 808
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.771660970979381e-05,
      "loss": 0.685,
      "step": 809
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.749759593097821e-05,
      "loss": 0.6278,
      "step": 810
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.72786957876918e-05,
      "loss": 0.6924,
      "step": 811
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.705991038536464e-05,
      "loss": 0.6418,
      "step": 812
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.684124082884732e-05,
      "loss": 0.6505,
      "step": 813
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.662268822240544e-05,
      "loss": 0.684,
      "step": 814
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.6404253669714e-05,
      "loss": 0.6891,
      "step": 815
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.618593827385187e-05,
      "loss": 0.6923,
      "step": 816
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.596774313729619e-05,
      "loss": 0.6334,
      "step": 817
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.574966936191675e-05,
      "loss": 0.6839,
      "step": 818
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.55317180489705e-05,
      "loss": 0.6733,
      "step": 819
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.531389029909591e-05,
      "loss": 0.6724,
      "step": 820
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.50961872123076e-05,
      "loss": 0.6709,
      "step": 821
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.487860988799054e-05,
      "loss": 0.6902,
      "step": 822
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.466115942489464e-05,
      "loss": 0.6791,
      "step": 823
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.444383692112919e-05,
      "loss": 0.6853,
      "step": 824
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.422664347415718e-05,
      "loss": 0.6574,
      "step": 825
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.400958018079008e-05,
      "loss": 0.6666,
      "step": 826
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.379264813718192e-05,
      "loss": 0.7201,
      "step": 827
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.357584843882398e-05,
      "loss": 0.6668,
      "step": 828
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.335918218053925e-05,
      "loss": 0.667,
      "step": 829
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.314265045647674e-05,
      "loss": 0.7202,
      "step": 830
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.292625436010625e-05,
      "loss": 0.6996,
      "step": 831
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.270999498421252e-05,
      "loss": 0.6645,
      "step": 832
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.249387342088992e-05,
      "loss": 0.6723,
      "step": 833
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.227789076153688e-05,
      "loss": 0.6882,
      "step": 834
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.206204809685029e-05,
      "loss": 0.6946,
      "step": 835
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.184634651682027e-05,
      "loss": 0.6743,
      "step": 836
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.163078711072427e-05,
      "loss": 0.7161,
      "step": 837
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.14153709671219e-05,
      "loss": 0.7519,
      "step": 838
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.120009917384921e-05,
      "loss": 0.6676,
      "step": 839
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.098497281801336e-05,
      "loss": 0.6516,
      "step": 840
    },
    {
      "epoch": 1.18,
      "learning_rate": 7.076999298598708e-05,
      "loss": 0.6706,
      "step": 841
    },
    {
      "epoch": 1.18,
      "learning_rate": 7.055516076340311e-05,
      "loss": 0.671,
      "step": 842
    },
    {
      "epoch": 1.18,
      "learning_rate": 7.034047723514876e-05,
      "loss": 0.6722,
      "step": 843
    },
    {
      "epoch": 1.18,
      "learning_rate": 7.012594348536049e-05,
      "loss": 0.6543,
      "step": 844
    },
    {
      "epoch": 1.18,
      "learning_rate": 6.991156059741836e-05,
      "loss": 0.6617,
      "step": 845
    },
    {
      "epoch": 1.18,
      "learning_rate": 6.969732965394064e-05,
      "loss": 0.6486,
      "step": 846
    },
    {
      "epoch": 1.18,
      "learning_rate": 6.948325173677826e-05,
      "loss": 0.6722,
      "step": 847
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.926932792700931e-05,
      "loss": 0.6905,
      "step": 848
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.905555930493374e-05,
      "loss": 0.7038,
      "step": 849
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.884194695006778e-05,
      "loss": 0.637,
      "step": 850
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.862849194113856e-05,
      "loss": 0.6119,
      "step": 851
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.841519535607859e-05,
      "loss": 0.6867,
      "step": 852
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.820205827202029e-05,
      "loss": 0.6527,
      "step": 853
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.798908176529071e-05,
      "loss": 0.6902,
      "step": 854
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.777626691140592e-05,
      "loss": 0.6562,
      "step": 855
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.756361478506578e-05,
      "loss": 0.66,
      "step": 856
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.735112646014825e-05,
      "loss": 0.6732,
      "step": 857
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.713880300970415e-05,
      "loss": 0.6463,
      "step": 858
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.692664550595169e-05,
      "loss": 0.6627,
      "step": 859
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.671465502027105e-05,
      "loss": 0.6773,
      "step": 860
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.650283262319909e-05,
      "loss": 0.6438,
      "step": 861
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.629117938442368e-05,
      "loss": 0.649,
      "step": 862
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.607969637277855e-05,
      "loss": 0.6492,
      "step": 863
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.586838465623773e-05,
      "loss": 0.6163,
      "step": 864
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.565724530191027e-05,
      "loss": 0.6706,
      "step": 865
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.54462793760348e-05,
      "loss": 0.6919,
      "step": 866
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.523548794397413e-05,
      "loss": 0.6707,
      "step": 867
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.502487207020993e-05,
      "loss": 0.6007,
      "step": 868
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.48144328183372e-05,
      "loss": 0.6883,
      "step": 869
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.460417125105918e-05,
      "loss": 0.6487,
      "step": 870
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.43940884301817e-05,
      "loss": 0.68,
      "step": 871
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.418418541660795e-05,
      "loss": 0.6465,
      "step": 872
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.397446327033313e-05,
      "loss": 0.6568,
      "step": 873
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.3764923050439e-05,
      "loss": 0.6548,
      "step": 874
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.355556581508878e-05,
      "loss": 0.6309,
      "step": 875
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.334639262152145e-05,
      "loss": 0.6943,
      "step": 876
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.313740452604664e-05,
      "loss": 0.6886,
      "step": 877
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.29286025840393e-05,
      "loss": 0.6466,
      "step": 878
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.271998784993425e-05,
      "loss": 0.6402,
      "step": 879
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.251156137722102e-05,
      "loss": 0.6694,
      "step": 880
    },
    {
      "epoch": 1.23,
      "eval_loss": 0.819640040397644,
      "eval_runtime": 57.9702,
      "eval_samples_per_second": 6.9,
      "eval_steps_per_second": 3.45,
      "step": 880
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.230332421843834e-05,
      "loss": 0.6827,
      "step": 881
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.209527742516895e-05,
      "loss": 0.6562,
      "step": 882
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.188742204803424e-05,
      "loss": 0.6963,
      "step": 883
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.167975913668898e-05,
      "loss": 0.6498,
      "step": 884
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.147228973981603e-05,
      "loss": 0.6537,
      "step": 885
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.1265014905121e-05,
      "loss": 0.6515,
      "step": 886
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.105793567932691e-05,
      "loss": 0.6486,
      "step": 887
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.085105310816905e-05,
      "loss": 0.6827,
      "step": 888
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.064436823638959e-05,
      "loss": 0.6615,
      "step": 889
    },
    {
      "epoch": 1.25,
      "learning_rate": 6.0437882107732335e-05,
      "loss": 0.6529,
      "step": 890
    },
    {
      "epoch": 1.25,
      "learning_rate": 6.0231595764937464e-05,
      "loss": 0.6978,
      "step": 891
    },
    {
      "epoch": 1.25,
      "learning_rate": 6.0025510249736196e-05,
      "loss": 0.6911,
      "step": 892
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.981962660284566e-05,
      "loss": 0.7181,
      "step": 893
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.9613945863963474e-05,
      "loss": 0.6847,
      "step": 894
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.940846907176272e-05,
      "loss": 0.6529,
      "step": 895
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.9203197263886434e-05,
      "loss": 0.6346,
      "step": 896
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.89981314769426e-05,
      "loss": 0.6549,
      "step": 897
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.8793272746498676e-05,
      "loss": 0.6211,
      "step": 898
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.858862210707661e-05,
      "loss": 0.6718,
      "step": 899
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.838418059214751e-05,
      "loss": 0.6829,
      "step": 900
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.8179949234126374e-05,
      "loss": 0.719,
      "step": 901
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.797592906436691e-05,
      "loss": 0.6637,
      "step": 902
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.77721211131564e-05,
      "loss": 0.641,
      "step": 903
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.756852640971035e-05,
      "loss": 0.662,
      "step": 904
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.736514598216748e-05,
      "loss": 0.7047,
      "step": 905
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.716198085758441e-05,
      "loss": 0.7097,
      "step": 906
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.695903206193043e-05,
      "loss": 0.731,
      "step": 907
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.675630062008239e-05,
      "loss": 0.6443,
      "step": 908
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.6553787555819596e-05,
      "loss": 0.6416,
      "step": 909
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.635149389181855e-05,
      "loss": 0.6841,
      "step": 910
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.6149420649647744e-05,
      "loss": 0.6402,
      "step": 911
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.594756884976255e-05,
      "loss": 0.6893,
      "step": 912
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.5745939511500155e-05,
      "loss": 0.6334,
      "step": 913
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.554453365307421e-05,
      "loss": 0.6559,
      "step": 914
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.5343352291569914e-05,
      "loss": 0.7165,
      "step": 915
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.5142396442938795e-05,
      "loss": 0.6668,
      "step": 916
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.494166712199343e-05,
      "loss": 0.6649,
      "step": 917
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.47411653424025e-05,
      "loss": 0.6687,
      "step": 918
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.454089211668567e-05,
      "loss": 0.6458,
      "step": 919
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.434084845620841e-05,
      "loss": 0.6971,
      "step": 920
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.414103537117683e-05,
      "loss": 0.6477,
      "step": 921
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.394145387063274e-05,
      "loss": 0.6785,
      "step": 922
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.3742104962448436e-05,
      "loss": 0.6921,
      "step": 923
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.354298965332156e-05,
      "loss": 0.6743,
      "step": 924
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.33441089487702e-05,
      "loss": 0.6489,
      "step": 925
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.314546385312773e-05,
      "loss": 0.6811,
      "step": 926
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.29470553695376e-05,
      "loss": 0.6952,
      "step": 927
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.2748884499948426e-05,
      "loss": 0.6592,
      "step": 928
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.2550952245108933e-05,
      "loss": 0.6499,
      "step": 929
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.2353259604562875e-05,
      "loss": 0.6516,
      "step": 930
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.215580757664385e-05,
      "loss": 0.6677,
      "step": 931
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.1958597158470546e-05,
      "loss": 0.6597,
      "step": 932
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.1761629345941376e-05,
      "loss": 0.6636,
      "step": 933
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.156490513372976e-05,
      "loss": 0.6772,
      "step": 934
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.1368425515278795e-05,
      "loss": 0.6314,
      "step": 935
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.117219148279658e-05,
      "loss": 0.6382,
      "step": 936
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.097620402725085e-05,
      "loss": 0.6261,
      "step": 937
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.0780464138364236e-05,
      "loss": 0.7056,
      "step": 938
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.058497280460923e-05,
      "loss": 0.6624,
      "step": 939
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.038973101320301e-05,
      "loss": 0.6907,
      "step": 940
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.0194739750102606e-05,
      "loss": 0.6418,
      "step": 941
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.6491,
      "step": 942
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.9805512746316965e-05,
      "loss": 0.6845,
      "step": 943
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.961127897120017e-05,
      "loss": 0.6894,
      "step": 944
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.9417299655516334e-05,
      "loss": 0.657,
      "step": 945
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.9223575778847085e-05,
      "loss": 0.6521,
      "step": 946
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.903010831948408e-05,
      "loss": 0.6504,
      "step": 947
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.883689825442418e-05,
      "loss": 0.6815,
      "step": 948
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.864394655936439e-05,
      "loss": 0.6427,
      "step": 949
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.845125420869696e-05,
      "loss": 0.6639,
      "step": 950
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.825882217550439e-05,
      "loss": 0.668,
      "step": 951
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.806665143155475e-05,
      "loss": 0.6969,
      "step": 952
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.787474294729647e-05,
      "loss": 0.6514,
      "step": 953
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.768309769185368e-05,
      "loss": 0.6569,
      "step": 954
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.7491716633021245e-05,
      "loss": 0.6529,
      "step": 955
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.730060073725976e-05,
      "loss": 0.6431,
      "step": 956
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.710975096969078e-05,
      "loss": 0.6295,
      "step": 957
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.6919168294091996e-05,
      "loss": 0.6553,
      "step": 958
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.672885367289233e-05,
      "loss": 0.6385,
      "step": 959
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.6538808067166885e-05,
      "loss": 0.6878,
      "step": 960
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.6349032436632454e-05,
      "loss": 0.6626,
      "step": 961
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.615952773964235e-05,
      "loss": 0.6713,
      "step": 962
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.597029493318168e-05,
      "loss": 0.6405,
      "step": 963
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.5781334972862586e-05,
      "loss": 0.6455,
      "step": 964
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.5592648812919406e-05,
      "loss": 0.6501,
      "step": 965
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.540423740620368e-05,
      "loss": 0.6512,
      "step": 966
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.521610170417947e-05,
      "loss": 0.6325,
      "step": 967
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.5028242656918664e-05,
      "loss": 0.6206,
      "step": 968
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.484066121309601e-05,
      "loss": 0.6791,
      "step": 969
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.4653358319984314e-05,
      "loss": 0.6088,
      "step": 970
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.446633492344984e-05,
      "loss": 0.6453,
      "step": 971
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.427959196794731e-05,
      "loss": 0.703,
      "step": 972
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.409313039651519e-05,
      "loss": 0.6491,
      "step": 973
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.390695115077124e-05,
      "loss": 0.6794,
      "step": 974
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.372105517090722e-05,
      "loss": 0.6484,
      "step": 975
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.353544339568448e-05,
      "loss": 0.6611,
      "step": 976
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.335011676242929e-05,
      "loss": 0.6632,
      "step": 977
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.316507620702779e-05,
      "loss": 0.6773,
      "step": 978
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.29803226639216e-05,
      "loss": 0.6443,
      "step": 979
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.279585706610282e-05,
      "loss": 0.6231,
      "step": 980
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.261168034510957e-05,
      "loss": 0.6842,
      "step": 981
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.242779343102108e-05,
      "loss": 0.638,
      "step": 982
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.224419725245302e-05,
      "loss": 0.6854,
      "step": 983
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.206089273655309e-05,
      "loss": 0.6331,
      "step": 984
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.187788080899591e-05,
      "loss": 0.7012,
      "step": 985
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.169516239397855e-05,
      "loss": 0.6863,
      "step": 986
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.151273841421599e-05,
      "loss": 0.639,
      "step": 987
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.1330609790936223e-05,
      "loss": 0.6973,
      "step": 988
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.114877744387581e-05,
      "loss": 0.6149,
      "step": 989
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.0967242291275e-05,
      "loss": 0.6305,
      "step": 990
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.078600524987339e-05,
      "loss": 0.6825,
      "step": 991
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.0605067234905016e-05,
      "loss": 0.661,
      "step": 992
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.04244291600939e-05,
      "loss": 0.698,
      "step": 993
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.0244091937649445e-05,
      "loss": 0.6191,
      "step": 994
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.0064056478261644e-05,
      "loss": 0.6526,
      "step": 995
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.988432369109667e-05,
      "loss": 0.6712,
      "step": 996
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.970489448379224e-05,
      "loss": 0.6701,
      "step": 997
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.952576976245307e-05,
      "loss": 0.6944,
      "step": 998
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.934695043164607e-05,
      "loss": 0.6565,
      "step": 999
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.916843739439614e-05,
      "loss": 0.646,
      "step": 1000
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.89902315521813e-05,
      "loss": 0.6692,
      "step": 1001
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.881233380492826e-05,
      "loss": 0.6371,
      "step": 1002
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.8634745051007925e-05,
      "loss": 0.6709,
      "step": 1003
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.845746618723084e-05,
      "loss": 0.673,
      "step": 1004
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.8280498108842536e-05,
      "loss": 0.6316,
      "step": 1005
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.8103841709519084e-05,
      "loss": 0.6491,
      "step": 1006
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.7927497881362695e-05,
      "loss": 0.6475,
      "step": 1007
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.775146751489712e-05,
      "loss": 0.6301,
      "step": 1008
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.7575751499063017e-05,
      "loss": 0.657,
      "step": 1009
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.7400350721213764e-05,
      "loss": 0.6903,
      "step": 1010
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.722526606711069e-05,
      "loss": 0.6502,
      "step": 1011
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.7050498420918686e-05,
      "loss": 0.6957,
      "step": 1012
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.6876048665202e-05,
      "loss": 0.6563,
      "step": 1013
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.670191768091933e-05,
      "loss": 0.6843,
      "step": 1014
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.652810634741963e-05,
      "loss": 0.6706,
      "step": 1015
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.6354615542437785e-05,
      "loss": 0.6568,
      "step": 1016
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.6181446142089856e-05,
      "loss": 0.6584,
      "step": 1017
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.6008599020868984e-05,
      "loss": 0.6578,
      "step": 1018
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.583607505164067e-05,
      "loss": 0.6717,
      "step": 1019
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.566387510563869e-05,
      "loss": 0.65,
      "step": 1020
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.5492000052460394e-05,
      "loss": 0.6768,
      "step": 1021
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.532045076006244e-05,
      "loss": 0.6677,
      "step": 1022
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.5149228094756595e-05,
      "loss": 0.6246,
      "step": 1023
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.497833292120499e-05,
      "loss": 0.6117,
      "step": 1024
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.4807766102415996e-05,
      "loss": 0.6396,
      "step": 1025
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.463752849973987e-05,
      "loss": 0.6862,
      "step": 1026
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.4467620972864276e-05,
      "loss": 0.6656,
      "step": 1027
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.429804437981008e-05,
      "loss": 0.6281,
      "step": 1028
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.412879957692696e-05,
      "loss": 0.6812,
      "step": 1029
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.3959887418889035e-05,
      "loss": 0.6806,
      "step": 1030
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.379130875869057e-05,
      "loss": 0.6553,
      "step": 1031
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.362306444764175e-05,
      "loss": 0.6733,
      "step": 1032
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.345515533536433e-05,
      "loss": 0.6767,
      "step": 1033
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.3287582269787285e-05,
      "loss": 0.6551,
      "step": 1034
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.312034609714255e-05,
      "loss": 0.6406,
      "step": 1035
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.29534476619609e-05,
      "loss": 0.6932,
      "step": 1036
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.278688780706741e-05,
      "loss": 0.6839,
      "step": 1037
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.262066737357744e-05,
      "loss": 0.6891,
      "step": 1038
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.245478720089233e-05,
      "loss": 0.6446,
      "step": 1039
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.228924812669503e-05,
      "loss": 0.6428,
      "step": 1040
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.2124050986945974e-05,
      "loss": 0.6749,
      "step": 1041
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.1959196615878936e-05,
      "loss": 0.6917,
      "step": 1042
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.1794685845996695e-05,
      "loss": 0.6273,
      "step": 1043
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.1630519508066815e-05,
      "loss": 0.631,
      "step": 1044
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.14666984311176e-05,
      "loss": 0.6335,
      "step": 1045
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.1303223442433726e-05,
      "loss": 0.655,
      "step": 1046
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.1140095367552156e-05,
      "loss": 0.67,
      "step": 1047
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.0977315030258e-05,
      "loss": 0.6778,
      "step": 1048
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.081488325258036e-05,
      "loss": 0.6719,
      "step": 1049
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.065280085478804e-05,
      "loss": 0.655,
      "step": 1050
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.04910686553855e-05,
      "loss": 0.6696,
      "step": 1051
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.0329687471108815e-05,
      "loss": 0.6697,
      "step": 1052
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.0168658116921433e-05,
      "loss": 0.6286,
      "step": 1053
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.000798140600999e-05,
      "loss": 0.6599,
      "step": 1054
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.9847658149780444e-05,
      "loss": 0.686,
      "step": 1055
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.9687689157853728e-05,
      "loss": 0.636,
      "step": 1056
    },
    {
      "epoch": 1.48,
      "eval_loss": 0.8143576383590698,
      "eval_runtime": 57.9785,
      "eval_samples_per_second": 6.899,
      "eval_steps_per_second": 3.45,
      "step": 1056
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.952807523806176e-05,
      "loss": 0.7033,
      "step": 1057
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.9368817196443443e-05,
      "loss": 0.6691,
      "step": 1058
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.9209915837240498e-05,
      "loss": 0.6354,
      "step": 1059
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.9051371962893358e-05,
      "loss": 0.6534,
      "step": 1060
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.8893186374037273e-05,
      "loss": 0.625,
      "step": 1061
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.873535986949817e-05,
      "loss": 0.6401,
      "step": 1062
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.8577893246288545e-05,
      "loss": 0.6459,
      "step": 1063
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.8420787299603558e-05,
      "loss": 0.6378,
      "step": 1064
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.826404282281705e-05,
      "loss": 0.63,
      "step": 1065
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.8107660607477338e-05,
      "loss": 0.6818,
      "step": 1066
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.7951641443303435e-05,
      "loss": 0.6667,
      "step": 1067
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.7795986118180982e-05,
      "loss": 0.6249,
      "step": 1068
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.76406954181582e-05,
      "loss": 0.6048,
      "step": 1069
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.748577012744198e-05,
      "loss": 0.6776,
      "step": 1070
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.7331211028393968e-05,
      "loss": 0.6305,
      "step": 1071
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.7177018901526565e-05,
      "loss": 0.6716,
      "step": 1072
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.7023194525498952e-05,
      "loss": 0.6863,
      "step": 1073
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.6869738677113186e-05,
      "loss": 0.6538,
      "step": 1074
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.671665213131037e-05,
      "loss": 0.6559,
      "step": 1075
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.656393566116653e-05,
      "loss": 0.6708,
      "step": 1076
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.6411590037888945e-05,
      "loss": 0.6336,
      "step": 1077
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.625961603081213e-05,
      "loss": 0.6629,
      "step": 1078
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.610801440739391e-05,
      "loss": 0.6722,
      "step": 1079
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.595678593321158e-05,
      "loss": 0.6703,
      "step": 1080
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.580593137195816e-05,
      "loss": 0.6392,
      "step": 1081
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.565545148543841e-05,
      "loss": 0.678,
      "step": 1082
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.5505347033564897e-05,
      "loss": 0.6811,
      "step": 1083
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.5355618774354438e-05,
      "loss": 0.6551,
      "step": 1084
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.5206267463923983e-05,
      "loss": 0.6392,
      "step": 1085
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.5057293856486918e-05,
      "loss": 0.6152,
      "step": 1086
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.490869870434933e-05,
      "loss": 0.6862,
      "step": 1087
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4760482757906133e-05,
      "loss": 0.6727,
      "step": 1088
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4612646765637192e-05,
      "loss": 0.6539,
      "step": 1089
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4465191474103676e-05,
      "loss": 0.6328,
      "step": 1090
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.431811762794427e-05,
      "loss": 0.6477,
      "step": 1091
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4171425969871385e-05,
      "loss": 0.6702,
      "step": 1092
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4025117240667337e-05,
      "loss": 0.6597,
      "step": 1093
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.387919217918079e-05,
      "loss": 0.6448,
      "step": 1094
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3733651522322832e-05,
      "loss": 0.6084,
      "step": 1095
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3588496005063287e-05,
      "loss": 0.6573,
      "step": 1096
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3443726360427252e-05,
      "loss": 0.6701,
      "step": 1097
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3299343319491005e-05,
      "loss": 0.6973,
      "step": 1098
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.315534761137853e-05,
      "loss": 0.6212,
      "step": 1099
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3011739963257904e-05,
      "loss": 0.6441,
      "step": 1100
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.2868521100337402e-05,
      "loss": 0.6869,
      "step": 1101
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.272569174586209e-05,
      "loss": 0.5995,
      "step": 1102
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.2583252621109917e-05,
      "loss": 0.6387,
      "step": 1103
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.244120444538833e-05,
      "loss": 0.6277,
      "step": 1104
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.229954793603041e-05,
      "loss": 0.6733,
      "step": 1105
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.2158283808391322e-05,
      "loss": 0.68,
      "step": 1106
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.2017412775844913e-05,
      "loss": 0.668,
      "step": 1107
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.1876935549779765e-05,
      "loss": 0.6527,
      "step": 1108
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.1736852839595768e-05,
      "loss": 0.6895,
      "step": 1109
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.159716535270063e-05,
      "loss": 0.6618,
      "step": 1110
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.1457873794506123e-05,
      "loss": 0.6772,
      "step": 1111
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.1318978868424643e-05,
      "loss": 0.6753,
      "step": 1112
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.118048127586567e-05,
      "loss": 0.6406,
      "step": 1113
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.1042381716232085e-05,
      "loss": 0.6527,
      "step": 1114
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.090468088691675e-05,
      "loss": 0.62,
      "step": 1115
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0767379483299032e-05,
      "loss": 0.6561,
      "step": 1116
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.06304781987412e-05,
      "loss": 0.6596,
      "step": 1117
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0493977724584924e-05,
      "loss": 0.6965,
      "step": 1118
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0357878750147784e-05,
      "loss": 0.6474,
      "step": 1119
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.022218196271992e-05,
      "loss": 0.6463,
      "step": 1120
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0086888047560327e-05,
      "loss": 0.645,
      "step": 1121
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.995199768789362e-05,
      "loss": 0.6118,
      "step": 1122
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9817511564906487e-05,
      "loss": 0.6454,
      "step": 1123
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9683430357744183e-05,
      "loss": 0.6051,
      "step": 1124
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9549754743507186e-05,
      "loss": 0.6658,
      "step": 1125
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9416485397247795e-05,
      "loss": 0.6451,
      "step": 1126
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9283622991966698e-05,
      "loss": 0.64,
      "step": 1127
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.915116819860947e-05,
      "loss": 0.6453,
      "step": 1128
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.9019121686063392e-05,
      "loss": 0.68,
      "step": 1129
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.888748412115383e-05,
      "loss": 0.6035,
      "step": 1130
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.8756256168641117e-05,
      "loss": 0.6455,
      "step": 1131
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.8625438491216975e-05,
      "loss": 0.634,
      "step": 1132
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.849503174950136e-05,
      "loss": 0.6768,
      "step": 1133
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.8365036602038933e-05,
      "loss": 0.6911,
      "step": 1134
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.8235453705295848e-05,
      "loss": 0.6201,
      "step": 1135
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.8106283713656547e-05,
      "loss": 0.6361,
      "step": 1136
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.7977527279420193e-05,
      "loss": 0.6341,
      "step": 1137
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.7849185052797523e-05,
      "loss": 0.6563,
      "step": 1138
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.7721257681907667e-05,
      "loss": 0.6747,
      "step": 1139
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.75937458127746e-05,
      "loss": 0.6672,
      "step": 1140
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.7466650089324212e-05,
      "loss": 0.6294,
      "step": 1141
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.733997115338074e-05,
      "loss": 0.663,
      "step": 1142
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.7213709644663788e-05,
      "loss": 0.6865,
      "step": 1143
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.7087866200784918e-05,
      "loss": 0.6875,
      "step": 1144
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.696244145724445e-05,
      "loss": 0.6641,
      "step": 1145
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.683743604742847e-05,
      "loss": 0.6546,
      "step": 1146
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.671285060260528e-05,
      "loss": 0.6353,
      "step": 1147
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.6588685751922438e-05,
      "loss": 0.6791,
      "step": 1148
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.6464942122403593e-05,
      "loss": 0.67,
      "step": 1149
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.6341620338945185e-05,
      "loss": 0.6755,
      "step": 1150
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.6218721024313388e-05,
      "loss": 0.6272,
      "step": 1151
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.609624479914098e-05,
      "loss": 0.6412,
      "step": 1152
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.5974192281924093e-05,
      "loss": 0.6268,
      "step": 1153
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.5852564089019185e-05,
      "loss": 0.6601,
      "step": 1154
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.573136083463993e-05,
      "loss": 0.6415,
      "step": 1155
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.5610583130854128e-05,
      "loss": 0.673,
      "step": 1156
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.5490231587580495e-05,
      "loss": 0.6886,
      "step": 1157
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.537030681258569e-05,
      "loss": 0.696,
      "step": 1158
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.5250809411481282e-05,
      "loss": 0.6441,
      "step": 1159
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.5131739987720539e-05,
      "loss": 0.6791,
      "step": 1160
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.5013099142595567e-05,
      "loss": 0.6655,
      "step": 1161
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.4894887475234132e-05,
      "loss": 0.5924,
      "step": 1162
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.4777105582596684e-05,
      "loss": 0.6731,
      "step": 1163
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.465975405947333e-05,
      "loss": 0.6823,
      "step": 1164
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.4542833498480867e-05,
      "loss": 0.6444,
      "step": 1165
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.4426344490059785e-05,
      "loss": 0.6407,
      "step": 1166
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.4310287622471186e-05,
      "loss": 0.6068,
      "step": 1167
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.419466348179399e-05,
      "loss": 0.6406,
      "step": 1168
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.40794726519218e-05,
      "loss": 0.5801,
      "step": 1169
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.396471571456004e-05,
      "loss": 0.6748,
      "step": 1170
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.3850393249223047e-05,
      "loss": 0.6777,
      "step": 1171
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3736505833231106e-05,
      "loss": 0.6374,
      "step": 1172
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3623054041707495e-05,
      "loss": 0.633,
      "step": 1173
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3510038447575613e-05,
      "loss": 0.6322,
      "step": 1174
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.6792,
      "step": 1175
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3285318132164093e-05,
      "loss": 0.6509,
      "step": 1176
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3173614545705937e-05,
      "loss": 0.6857,
      "step": 1177
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3062349426276831e-05,
      "loss": 0.7007,
      "step": 1178
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.295152333575762e-05,
      "loss": 0.6481,
      "step": 1179
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.2841136833812118e-05,
      "loss": 0.6593,
      "step": 1180
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.273119047788428e-05,
      "loss": 0.6251,
      "step": 1181
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.2621684823195334e-05,
      "loss": 0.6387,
      "step": 1182
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.2512620422740973e-05,
      "loss": 0.6419,
      "step": 1183
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.2403997827288638e-05,
      "loss": 0.6826,
      "step": 1184
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.2295817585374614e-05,
      "loss": 0.6811,
      "step": 1185
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.2188080243301437e-05,
      "loss": 0.6796,
      "step": 1186
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.2080786345134897e-05,
      "loss": 0.6602,
      "step": 1187
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.1973936432701571e-05,
      "loss": 0.6405,
      "step": 1188
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.18675310455858e-05,
      "loss": 0.6663,
      "step": 1189
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.176157072112719e-05,
      "loss": 0.6427,
      "step": 1190
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.1656055994417836e-05,
      "loss": 0.6509,
      "step": 1191
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.1550987398299506e-05,
      "loss": 0.6341,
      "step": 1192
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.1446365463361075e-05,
      "loss": 0.649,
      "step": 1193
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.1342190717935852e-05,
      "loss": 0.6986,
      "step": 1194
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.1238463688098844e-05,
      "loss": 0.6315,
      "step": 1195
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.1135184897664119e-05,
      "loss": 0.6358,
      "step": 1196
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.1032354868182149e-05,
      "loss": 0.6514,
      "step": 1197
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.0929974118937259e-05,
      "loss": 0.6525,
      "step": 1198
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.0828043166944857e-05,
      "loss": 0.6924,
      "step": 1199
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.072656252694898e-05,
      "loss": 0.6344,
      "step": 1200
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0625532711419606e-05,
      "loss": 0.6564,
      "step": 1201
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0524954230550043e-05,
      "loss": 0.6352,
      "step": 1202
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0424827592254416e-05,
      "loss": 0.6591,
      "step": 1203
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0325153302165081e-05,
      "loss": 0.6213,
      "step": 1204
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.022593186363009e-05,
      "loss": 0.6592,
      "step": 1205
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0127163777710569e-05,
      "loss": 0.6497,
      "step": 1206
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.002884954317831e-05,
      "loss": 0.6876,
      "step": 1207
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.930989656513145e-06,
      "loss": 0.6584,
      "step": 1208
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.83358461190047e-06,
      "loss": 0.6674,
      "step": 1209
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.736634901228814e-06,
      "loss": 0.6506,
      "step": 1210
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.640141014087267e-06,
      "loss": 0.6173,
      "step": 1211
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.544103437763063e-06,
      "loss": 0.6649,
      "step": 1212
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.448522657239045e-06,
      "loss": 0.6055,
      "step": 1213
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.353399155191333e-06,
      "loss": 0.6883,
      "step": 1214
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.25873341198683e-06,
      "loss": 0.7119,
      "step": 1215
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.164525905680709e-06,
      "loss": 0.6599,
      "step": 1216
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.070777112014173e-06,
      "loss": 0.6102,
      "step": 1217
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.977487504411897e-06,
      "loss": 0.6979,
      "step": 1218
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.884657553979692e-06,
      "loss": 0.6645,
      "step": 1219
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.792287729502213e-06,
      "loss": 0.6878,
      "step": 1220
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.700378497440443e-06,
      "loss": 0.6747,
      "step": 1221
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.608930321929398e-06,
      "loss": 0.6595,
      "step": 1222
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.517943664775851e-06,
      "loss": 0.6182,
      "step": 1223
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.42741898545586e-06,
      "loss": 0.6556,
      "step": 1224
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.337356741112623e-06,
      "loss": 0.6433,
      "step": 1225
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.247757386553989e-06,
      "loss": 0.6376,
      "step": 1226
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.158621374250307e-06,
      "loss": 0.6361,
      "step": 1227
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.069949154332045e-06,
      "loss": 0.6697,
      "step": 1228
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.98174117458752e-06,
      "loss": 0.6604,
      "step": 1229
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.893997880460802e-06,
      "loss": 0.6632,
      "step": 1230
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.806719715049193e-06,
      "loss": 0.6572,
      "step": 1231
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.719907119101177e-06,
      "loss": 0.6842,
      "step": 1232
    },
    {
      "epoch": 1.73,
      "eval_loss": 0.8104925155639648,
      "eval_runtime": 57.9856,
      "eval_samples_per_second": 6.898,
      "eval_steps_per_second": 3.449,
      "step": 1232
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.63356053101415e-06,
      "loss": 0.6209,
      "step": 1233
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.547680386832201e-06,
      "loss": 0.6393,
      "step": 1234
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.462267120243905e-06,
      "loss": 0.668,
      "step": 1235
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.377321162580153e-06,
      "loss": 0.6604,
      "step": 1236
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.2928429428119505e-06,
      "loss": 0.641,
      "step": 1237
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.2088328875482335e-06,
      "loss": 0.6395,
      "step": 1238
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.125291421033775e-06,
      "loss": 0.7054,
      "step": 1239
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.042218965147029e-06,
      "loss": 0.6438,
      "step": 1240
    },
    {
      "epoch": 1.74,
      "learning_rate": 6.959615939397912e-06,
      "loss": 0.6233,
      "step": 1241
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.877482760925791e-06,
      "loss": 0.628,
      "step": 1242
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.795819844497364e-06,
      "loss": 0.6321,
      "step": 1243
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.714627602504475e-06,
      "loss": 0.6676,
      "step": 1244
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.633906444962146e-06,
      "loss": 0.6937,
      "step": 1245
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.553656779506468e-06,
      "loss": 0.6587,
      "step": 1246
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.4738790113924805e-06,
      "loss": 0.6379,
      "step": 1247
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.394573543492188e-06,
      "loss": 0.6681,
      "step": 1248
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.315740776292534e-06,
      "loss": 0.6625,
      "step": 1249
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.23738110789337e-06,
      "loss": 0.6226,
      "step": 1250
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.1594949340053834e-06,
      "loss": 0.6315,
      "step": 1251
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.082082647948195e-06,
      "loss": 0.6793,
      "step": 1252
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.005144640648286e-06,
      "loss": 0.6392,
      "step": 1253
    },
    {
      "epoch": 1.76,
      "learning_rate": 5.928681300637096e-06,
      "loss": 0.6346,
      "step": 1254
    },
    {
      "epoch": 1.76,
      "learning_rate": 5.852693014049004e-06,
      "loss": 0.659,
      "step": 1255
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.7771801646194445e-06,
      "loss": 0.6297,
      "step": 1256
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.70214313368288e-06,
      "loss": 0.6203,
      "step": 1257
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.627582300170908e-06,
      "loss": 0.6401,
      "step": 1258
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.553498040610472e-06,
      "loss": 0.7036,
      "step": 1259
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.479890729121739e-06,
      "loss": 0.6315,
      "step": 1260
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.4067607374163496e-06,
      "loss": 0.6498,
      "step": 1261
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.334108434795548e-06,
      "loss": 0.6549,
      "step": 1262
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.261934188148243e-06,
      "loss": 0.6283,
      "step": 1263
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.190238361949229e-06,
      "loss": 0.6373,
      "step": 1264
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.119021318257267e-06,
      "loss": 0.6413,
      "step": 1265
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.048283416713362e-06,
      "loss": 0.6813,
      "step": 1266
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.978025014538823e-06,
      "loss": 0.7072,
      "step": 1267
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.908246466533562e-06,
      "loss": 0.6503,
      "step": 1268
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.838948125074261e-06,
      "loss": 0.6933,
      "step": 1269
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.770130340112566e-06,
      "loss": 0.6409,
      "step": 1270
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.7017934591733535e-06,
      "loss": 0.6477,
      "step": 1271
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.633937827353008e-06,
      "loss": 0.6494,
      "step": 1272
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.56656378731759e-06,
      "loss": 0.653,
      "step": 1273
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.499671679301176e-06,
      "loss": 0.65,
      "step": 1274
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.433261841104141e-06,
      "loss": 0.6249,
      "step": 1275
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.367334608091389e-06,
      "loss": 0.655,
      "step": 1276
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.301890313190738e-06,
      "loss": 0.6463,
      "step": 1277
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.236929286891189e-06,
      "loss": 0.6175,
      "step": 1278
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.172451857241278e-06,
      "loss": 0.6669,
      "step": 1279
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.108458349847411e-06,
      "loss": 0.6378,
      "step": 1280
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.0449490878721855e-06,
      "loss": 0.6449,
      "step": 1281
    },
    {
      "epoch": 1.8,
      "learning_rate": 3.981924392032876e-06,
      "loss": 0.6559,
      "step": 1282
    },
    {
      "epoch": 1.8,
      "learning_rate": 3.919384580599639e-06,
      "loss": 0.6546,
      "step": 1283
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.8573299693940635e-06,
      "loss": 0.6245,
      "step": 1284
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.7957608717875015e-06,
      "loss": 0.6872,
      "step": 1285
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.7346775986994763e-06,
      "loss": 0.7109,
      "step": 1286
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.6740804585961407e-06,
      "loss": 0.6207,
      "step": 1287
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.613969757488711e-06,
      "loss": 0.6629,
      "step": 1288
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.554345798931935e-06,
      "loss": 0.6732,
      "step": 1289
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.4952088840225273e-06,
      "loss": 0.6228,
      "step": 1290
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.43655931139768e-06,
      "loss": 0.6476,
      "step": 1291
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.378397377233522e-06,
      "loss": 0.7001,
      "step": 1292
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.3207233752436617e-06,
      "loss": 0.6188,
      "step": 1293
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.263537596677668e-06,
      "loss": 0.6096,
      "step": 1294
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.2068403303196604e-06,
      "loss": 0.6508,
      "step": 1295
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.1506318624867527e-06,
      "loss": 0.7394,
      "step": 1296
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.094912477027667e-06,
      "loss": 0.6773,
      "step": 1297
    },
    {
      "epoch": 1.83,
      "learning_rate": 3.0396824553213244e-06,
      "loss": 0.646,
      "step": 1298
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.984942076275399e-06,
      "loss": 0.6592,
      "step": 1299
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.9306916163248543e-06,
      "loss": 0.6327,
      "step": 1300
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.876931349430656e-06,
      "loss": 0.686,
      "step": 1301
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.8236615470782825e-06,
      "loss": 0.6208,
      "step": 1302
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.7708824782764154e-06,
      "loss": 0.6916,
      "step": 1303
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.718594409555575e-06,
      "loss": 0.6745,
      "step": 1304
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.6667976049667977e-06,
      "loss": 0.6582,
      "step": 1305
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.6154923260801934e-06,
      "loss": 0.6279,
      "step": 1306
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.56467883198378e-06,
      "loss": 0.6387,
      "step": 1307
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.5143573792820286e-06,
      "loss": 0.6572,
      "step": 1308
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.46452822209472e-06,
      "loss": 0.6331,
      "step": 1309
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.4151916120554784e-06,
      "loss": 0.6347,
      "step": 1310
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.3663477983106862e-06,
      "loss": 0.6476,
      "step": 1311
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.317997027518104e-06,
      "loss": 0.6878,
      "step": 1312
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.2701395438456286e-06,
      "loss": 0.6796,
      "step": 1313
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.2227755889701607e-06,
      "loss": 0.6435,
      "step": 1314
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.1759054020762835e-06,
      "loss": 0.5924,
      "step": 1315
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.129529219855053e-06,
      "loss": 0.5882,
      "step": 1316
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.083647276502887e-06,
      "loss": 0.6906,
      "step": 1317
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.0382598037203215e-06,
      "loss": 0.6497,
      "step": 1318
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.9933670307108354e-06,
      "loss": 0.6008,
      "step": 1319
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.948969184179705e-06,
      "loss": 0.6486,
      "step": 1320
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.9050664883328962e-06,
      "loss": 0.68,
      "step": 1321
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.861659164875873e-06,
      "loss": 0.6331,
      "step": 1322
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.818747433012502e-06,
      "loss": 0.6639,
      "step": 1323
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.7763315094439737e-06,
      "loss": 0.6563,
      "step": 1324
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.7344116083676587e-06,
      "loss": 0.576,
      "step": 1325
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.692987941476032e-06,
      "loss": 0.6783,
      "step": 1326
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.6520607179556725e-06,
      "loss": 0.6525,
      "step": 1327
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.6116301444861315e-06,
      "loss": 0.6624,
      "step": 1328
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.5716964252388889e-06,
      "loss": 0.6464,
      "step": 1329
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.5322597618763756e-06,
      "loss": 0.6258,
      "step": 1330
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.493320353550931e-06,
      "loss": 0.6796,
      "step": 1331
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.4548783969037471e-06,
      "loss": 0.6478,
      "step": 1332
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.4169340860639812e-06,
      "loss": 0.7504,
      "step": 1333
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.3794876126476785e-06,
      "loss": 0.6526,
      "step": 1334
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.342539165756851e-06,
      "loss": 0.6679,
      "step": 1335
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.3060889319784885e-06,
      "loss": 0.6506,
      "step": 1336
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.2701370953836834e-06,
      "loss": 0.6489,
      "step": 1337
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.2346838375266401e-06,
      "loss": 0.6222,
      "step": 1338
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.1997293374437556e-06,
      "loss": 0.6534,
      "step": 1339
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.165273771652764e-06,
      "loss": 0.6419,
      "step": 1340
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.131317314151803e-06,
      "loss": 0.6639,
      "step": 1341
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.097860136418527e-06,
      "loss": 0.6043,
      "step": 1342
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.0649024074093294e-06,
      "loss": 0.7119,
      "step": 1343
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.0324442935583545e-06,
      "loss": 0.6543,
      "step": 1344
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.0004859587767645e-06,
      "loss": 0.683,
      "step": 1345
    },
    {
      "epoch": 1.89,
      "learning_rate": 9.69027564451852e-07,
      "loss": 0.6534,
      "step": 1346
    },
    {
      "epoch": 1.89,
      "learning_rate": 9.380692694462623e-07,
      "loss": 0.6257,
      "step": 1347
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.076112300971717e-07,
      "loss": 0.6352,
      "step": 1348
    },
    {
      "epoch": 1.9,
      "learning_rate": 8.776536002154889e-07,
      "loss": 0.6545,
      "step": 1349
    },
    {
      "epoch": 1.9,
      "learning_rate": 8.481965310851103e-07,
      "loss": 0.6413,
      "step": 1350
    },
    {
      "epoch": 1.9,
      "learning_rate": 8.192401714621101e-07,
      "loss": 0.6137,
      "step": 1351
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.907846675740293e-07,
      "loss": 0.7088,
      "step": 1352
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.628301631191547e-07,
      "loss": 0.6226,
      "step": 1353
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.353767992657079e-07,
      "loss": 0.6652,
      "step": 1354
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.084247146512124e-07,
      "loss": 0.6825,
      "step": 1355
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.819740453817724e-07,
      "loss": 0.6646,
      "step": 1356
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.560249250313622e-07,
      "loss": 0.638,
      "step": 1357
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.305774846411927e-07,
      "loss": 0.6435,
      "step": 1358
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.05631852719013e-07,
      "loss": 0.6033,
      "step": 1359
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.811881552384768e-07,
      "loss": 0.6646,
      "step": 1360
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.572465156384987e-07,
      "loss": 0.6382,
      "step": 1361
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.338070548226549e-07,
      "loss": 0.6062,
      "step": 1362
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.108698911585385e-07,
      "loss": 0.6745,
      "step": 1363
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.884351404771947e-07,
      "loss": 0.6538,
      "step": 1364
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.6650291607248653e-07,
      "loss": 0.6445,
      "step": 1365
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.4507332870059594e-07,
      "loss": 0.6623,
      "step": 1366
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.2414648657940204e-07,
      "loss": 0.5762,
      "step": 1367
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.0372249538793703e-07,
      "loss": 0.6286,
      "step": 1368
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.8380145826593105e-07,
      "loss": 0.6167,
      "step": 1369
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.6438347581316814e-07,
      "loss": 0.6501,
      "step": 1370
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.4546864608907546e-07,
      "loss": 0.605,
      "step": 1371
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.2705706461219064e-07,
      "loss": 0.6469,
      "step": 1372
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.0914882435967296e-07,
      "loss": 0.6201,
      "step": 1373
    },
    {
      "epoch": 1.93,
      "learning_rate": 2.917440157668705e-07,
      "loss": 0.662,
      "step": 1374
    },
    {
      "epoch": 1.93,
      "learning_rate": 2.7484272672680946e-07,
      "loss": 0.6506,
      "step": 1375
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.584450425897833e-07,
      "loss": 0.6556,
      "step": 1376
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.4255104616294213e-07,
      "loss": 0.6475,
      "step": 1377
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.271608177098039e-07,
      "loss": 0.6183,
      "step": 1378
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.1227443494994393e-07,
      "loss": 0.6411,
      "step": 1379
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.9789197305851716e-07,
      "loss": 0.6051,
      "step": 1380
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.8401350466592526e-07,
      "loss": 0.6265,
      "step": 1381
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.706390998574392e-07,
      "loss": 0.653,
      "step": 1382
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.5776882617285493e-07,
      "loss": 0.6495,
      "step": 1383
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.4540274860612712e-07,
      "loss": 0.6646,
      "step": 1384
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.3354092960505826e-07,
      "loss": 0.6629,
      "step": 1385
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.2218342907099888e-07,
      "loss": 0.6599,
      "step": 1386
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.1133030435849234e-07,
      "loss": 0.6826,
      "step": 1387
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.009816102750527e-07,
      "loss": 0.6781,
      "step": 1388
    },
    {
      "epoch": 1.95,
      "learning_rate": 9.113739908084285e-08,
      "loss": 0.6226,
      "step": 1389
    },
    {
      "epoch": 1.96,
      "learning_rate": 8.179772048843015e-08,
      "loss": 0.6726,
      "step": 1390
    },
    {
      "epoch": 1.96,
      "learning_rate": 7.29626216625201e-08,
      "loss": 0.6393,
      "step": 1391
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.4632147219712e-08,
      "loss": 0.6697,
      "step": 1392
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.680633922833245e-08,
      "loss": 0.6606,
      "step": 1393
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.9485237208135585e-08,
      "loss": 0.647,
      "step": 1394
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.2668878130169843e-08,
      "loss": 0.6056,
      "step": 1395
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.635729641654484e-08,
      "loss": 0.6517,
      "step": 1396
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.055052394030922e-08,
      "loss": 0.672,
      "step": 1397
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.5248590025250818e-08,
      "loss": 0.6555,
      "step": 1398
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.0451521445752352e-08,
      "loss": 0.6657,
      "step": 1399
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.6159342426669278e-08,
      "loss": 0.67,
      "step": 1400
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.237207464318546e-08,
      "loss": 0.6673,
      "step": 1401
    },
    {
      "epoch": 1.97,
      "learning_rate": 9.089737220746574e-09,
      "loss": 0.6763,
      "step": 1402
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.312346734915764e-09,
      "loss": 0.6919,
      "step": 1403
    },
    {
      "epoch": 1.98,
      "learning_rate": 4.039917211318134e-09,
      "loss": 0.6504,
      "step": 1404
    },
    {
      "epoch": 1.98,
      "learning_rate": 2.272460125563036e-09,
      "loss": 0.6561,
      "step": 1405
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.0099844031774553e-09,
      "loss": 0.6636,
      "step": 1406
    },
    {
      "epoch": 1.98,
      "learning_rate": 2.5249641956159865e-10,
      "loss": 0.6112,
      "step": 1407
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0,
      "loss": 0.6277,
      "step": 1408
    },
    {
      "epoch": 1.98,
      "eval_loss": 0.8100082278251648,
      "eval_runtime": 58.013,
      "eval_samples_per_second": 6.895,
      "eval_steps_per_second": 3.448,
      "step": 1408
    }
  ],
  "logging_steps": 1,
  "max_steps": 1408,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 704,
  "total_flos": 4.7940109707352474e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}