{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9818780889621088,
  "eval_steps": 152,
  "global_step": 1214,
  "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": 1.0107,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.0285824537277222,
      "eval_runtime": 85.1275,
      "eval_samples_per_second": 4.041,
      "eval_steps_per_second": 2.02,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 1.0286,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-05,
      "loss": 1.0509,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 1.0267,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.0035,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012,
      "loss": 0.98,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014,
      "loss": 0.8973,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016,
      "loss": 0.9456,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018,
      "loss": 0.9843,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.926,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999965957885393,
      "loss": 0.9399,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001999986383177335,
      "loss": 0.8926,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999693622359184,
      "loss": 0.9118,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001999945533080175,
      "loss": 0.9197,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999148958723447,
      "loss": 0.9105,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001999877450821018,
      "loss": 0.8527,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019998331981811366,
      "loss": 0.8422,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001999782138253991,
      "loss": 0.8741,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019997242713872196,
      "loss": 0.8792,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019996595979748037,
      "loss": 0.8766,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019995881184570676,
      "loss": 0.8361,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019995098333206742,
      "loss": 0.8709,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019994247430986213,
      "loss": 0.8575,
      "step": 23
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019993328483702393,
      "loss": 0.8293,
      "step": 24
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999234149761187,
      "loss": 0.8589,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019991286479434454,
      "loss": 0.8203,
      "step": 26
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999016343635316,
      "loss": 0.8196,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019988972376014142,
      "loss": 0.8936,
      "step": 28
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019987713306526638,
      "loss": 0.9094,
      "step": 29
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019986386236462924,
      "loss": 0.8147,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019984991174858257,
      "loss": 0.875,
      "step": 31
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019983528131210812,
      "loss": 0.8109,
      "step": 32
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019981997115481602,
      "loss": 0.8138,
      "step": 33
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019980398138094428,
      "loss": 0.786,
      "step": 34
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001997873120993581,
      "loss": 0.8516,
      "step": 35
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019976996342354898,
      "loss": 0.8395,
      "step": 36
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019975193547163404,
      "loss": 0.8347,
      "step": 37
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019973322836635518,
      "loss": 0.8074,
      "step": 38
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001997138422350783,
      "loss": 0.8411,
      "step": 39
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019969377720979237,
      "loss": 0.8197,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019967303342710864,
      "loss": 0.8325,
      "step": 41
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019965161102825945,
      "loss": 0.8291,
      "step": 42
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001996295101590976,
      "loss": 0.8414,
      "step": 43
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019960673097009518,
      "loss": 0.85,
      "step": 44
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019958327361634248,
      "loss": 0.8324,
      "step": 45
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019955913825754713,
      "loss": 0.8225,
      "step": 46
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019953432505803286,
      "loss": 0.8364,
      "step": 47
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001995088341867384,
      "loss": 0.8513,
      "step": 48
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019948266581721642,
      "loss": 0.8739,
      "step": 49
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001994558201276322,
      "loss": 0.8212,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019942829730076257,
      "loss": 0.8821,
      "step": 51
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001994000975239946,
      "loss": 0.8511,
      "step": 52
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019937122098932428,
      "loss": 0.8369,
      "step": 53
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019934166789335525,
      "loss": 0.8224,
      "step": 54
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019931143843729748,
      "loss": 0.7896,
      "step": 55
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019928053282696596,
      "loss": 0.8295,
      "step": 56
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019924895127277907,
      "loss": 0.8231,
      "step": 57
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019921669398975745,
      "loss": 0.8321,
      "step": 58
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001991837611975223,
      "loss": 0.8051,
      "step": 59
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000199150153120294,
      "loss": 0.8772,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001991158699868905,
      "loss": 0.8126,
      "step": 61
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019908091203072598,
      "loss": 0.8615,
      "step": 62
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019904527948980894,
      "loss": 0.8272,
      "step": 63
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019900897260674073,
      "loss": 0.8134,
      "step": 64
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019897199162871408,
      "loss": 0.8558,
      "step": 65
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019893433680751103,
      "loss": 0.8155,
      "step": 66
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019889600839950155,
      "loss": 0.8504,
      "step": 67
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001988570066656417,
      "loss": 0.7906,
      "step": 68
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019881733187147171,
      "loss": 0.8246,
      "step": 69
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019877698428711442,
      "loss": 0.8345,
      "step": 70
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001987359641872732,
      "loss": 0.8161,
      "step": 71
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019869427185123027,
      "loss": 0.8307,
      "step": 72
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019865190756284467,
      "loss": 0.8157,
      "step": 73
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019860887161055038,
      "loss": 0.8138,
      "step": 74
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001985651642873544,
      "loss": 0.8162,
      "step": 75
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019852078589083466,
      "loss": 0.8313,
      "step": 76
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019847573672313802,
      "loss": 0.8081,
      "step": 77
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001984300170909783,
      "loss": 0.7811,
      "step": 78
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019838362730563406,
      "loss": 0.833,
      "step": 79
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019833656768294662,
      "loss": 0.8214,
      "step": 80
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019828883854331776,
      "loss": 0.8096,
      "step": 81
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001982404402117077,
      "loss": 0.855,
      "step": 82
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019819137301763267,
      "loss": 0.8122,
      "step": 83
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019814163729516292,
      "loss": 0.8423,
      "step": 84
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001980912333829203,
      "loss": 0.83,
      "step": 85
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001980401616240759,
      "loss": 0.8439,
      "step": 86
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019798842236634797,
      "loss": 0.7693,
      "step": 87
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019793601596199912,
      "loss": 0.8443,
      "step": 88
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019788294276783442,
      "loss": 0.8203,
      "step": 89
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019782920314519856,
      "loss": 0.7918,
      "step": 90
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019777479745997366,
      "loss": 0.856,
      "step": 91
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019771972608257659,
      "loss": 0.8001,
      "step": 92
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019766398938795662,
      "loss": 0.7688,
      "step": 93
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019760758775559274,
      "loss": 0.8188,
      "step": 94
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019755052156949105,
      "loss": 0.81,
      "step": 95
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.8473,
      "step": 96
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001974343970947193,
      "loss": 0.7996,
      "step": 97
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001973753395966737,
      "loss": 0.7884,
      "step": 98
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019731561912613406,
      "loss": 0.829,
      "step": 99
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019725523608970255,
      "loss": 0.7999,
      "step": 100
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019719419089849247,
      "loss": 0.8344,
      "step": 101
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019713248396812524,
      "loss": 0.8108,
      "step": 102
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019707011571872777,
      "loss": 0.8543,
      "step": 103
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019700708657492948,
      "loss": 0.7791,
      "step": 104
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019694339696585942,
      "loss": 0.8245,
      "step": 105
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001968790473251434,
      "loss": 0.8192,
      "step": 106
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019681403809090097,
      "loss": 0.826,
      "step": 107
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019674836970574254,
      "loss": 0.8262,
      "step": 108
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019668204261676618,
      "loss": 0.7775,
      "step": 109
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019661505727555482,
      "loss": 0.7647,
      "step": 110
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019654741413817296,
      "loss": 0.8048,
      "step": 111
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001964791136651637,
      "loss": 0.8262,
      "step": 112
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019641015632154552,
      "loss": 0.8083,
      "step": 113
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019634054257680923,
      "loss": 0.7768,
      "step": 114
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019627027290491458,
      "loss": 0.794,
      "step": 115
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001961993477842873,
      "loss": 0.8039,
      "step": 116
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019612776769781554,
      "loss": 0.7718,
      "step": 117
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001960555331328468,
      "loss": 0.7891,
      "step": 118
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019598264458118458,
      "loss": 0.87,
      "step": 119
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019590910253908494,
      "loss": 0.8009,
      "step": 120
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019583490750725325,
      "loss": 0.7793,
      "step": 121
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001957600599908406,
      "loss": 0.755,
      "step": 122
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001956845604994406,
      "loss": 0.8324,
      "step": 123
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019560840954708565,
      "loss": 0.801,
      "step": 124
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019553160765224372,
      "loss": 0.7857,
      "step": 125
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001954541553378145,
      "loss": 0.7975,
      "step": 126
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001953760531311262,
      "loss": 0.7837,
      "step": 127
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001952973015639316,
      "loss": 0.7926,
      "step": 128
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001952179011724047,
      "loss": 0.7713,
      "step": 129
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019513785249713697,
      "loss": 0.7883,
      "step": 130
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019505715608313359,
      "loss": 0.8101,
      "step": 131
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019497581247980992,
      "loss": 0.8487,
      "step": 132
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001948938222409876,
      "loss": 0.7866,
      "step": 133
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019481118592489086,
      "loss": 0.8004,
      "step": 134
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019472790409414266,
      "loss": 0.8064,
      "step": 135
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019464397731576094,
      "loss": 0.8209,
      "step": 136
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019455940616115472,
      "loss": 0.8289,
      "step": 137
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019447419120612017,
      "loss": 0.7755,
      "step": 138
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019438833303083678,
      "loss": 0.7701,
      "step": 139
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019430183221986325,
      "loss": 0.7563,
      "step": 140
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001942146893621337,
      "loss": 0.7749,
      "step": 141
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019412690505095365,
      "loss": 0.8033,
      "step": 142
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001940384798839957,
      "loss": 0.8116,
      "step": 143
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019394941446329583,
      "loss": 0.7957,
      "step": 144
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001938597093952491,
      "loss": 0.7991,
      "step": 145
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019376936529060554,
      "loss": 0.7871,
      "step": 146
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000193678382764466,
      "loss": 0.8345,
      "step": 147
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019358676243627808,
      "loss": 0.7805,
      "step": 148
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019349450492983164,
      "loss": 0.8089,
      "step": 149
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001934016108732548,
      "loss": 0.7563,
      "step": 150
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019330808089900963,
      "loss": 0.7729,
      "step": 151
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019321391564388775,
      "loss": 0.8198,
      "step": 152
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.8079261183738708,
      "eval_runtime": 85.1654,
      "eval_samples_per_second": 4.039,
      "eval_steps_per_second": 2.02,
      "step": 152
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019311911574900598,
      "loss": 0.7712,
      "step": 153
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019302368185980217,
      "loss": 0.7539,
      "step": 154
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019292761462603056,
      "loss": 0.7872,
      "step": 155
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019283091470175754,
      "loss": 0.7657,
      "step": 156
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019273358274535704,
      "loss": 0.7503,
      "step": 157
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019263561941950622,
      "loss": 0.7753,
      "step": 158
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001925370253911808,
      "loss": 0.8214,
      "step": 159
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019243780133165067,
      "loss": 0.839,
      "step": 160
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019233794791647516,
      "loss": 0.7858,
      "step": 161
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019223746582549853,
      "loss": 0.8081,
      "step": 162
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001921363557428454,
      "loss": 0.7762,
      "step": 163
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019203461835691594,
      "loss": 0.7837,
      "step": 164
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019193225436038133,
      "loss": 0.816,
      "step": 165
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019182926445017893,
      "loss": 0.7962,
      "step": 166
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001917256493275076,
      "loss": 0.8454,
      "step": 167
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019162140969782292,
      "loss": 0.7748,
      "step": 168
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019151654627083236,
      "loss": 0.782,
      "step": 169
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019141105976049053,
      "loss": 0.8049,
      "step": 170
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001913049508849942,
      "loss": 0.7263,
      "step": 171
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019119822036677738,
      "loss": 0.8035,
      "step": 172
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019109086893250664,
      "loss": 0.7649,
      "step": 173
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000190982897313076,
      "loss": 0.8311,
      "step": 174
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001908743062436018,
      "loss": 0.8503,
      "step": 175
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019076509646341806,
      "loss": 0.7664,
      "step": 176
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019065526871607112,
      "loss": 0.805,
      "step": 177
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019054482374931467,
      "loss": 0.7798,
      "step": 178
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019043376231510484,
      "loss": 0.804,
      "step": 179
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001903220851695948,
      "loss": 0.8074,
      "step": 180
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001902097930731298,
      "loss": 0.8134,
      "step": 181
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.7793,
      "step": 182
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018998336708964488,
      "loss": 0.793,
      "step": 183
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018986923474422884,
      "loss": 0.781,
      "step": 184
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018975449053105505,
      "loss": 0.858,
      "step": 185
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001896391352313506,
      "loss": 0.7909,
      "step": 186
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018952316963050328,
      "loss": 0.7954,
      "step": 187
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001894065945180558,
      "loss": 0.7544,
      "step": 188
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018928941068770093,
      "loss": 0.7575,
      "step": 189
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001891716189372757,
      "loss": 0.7981,
      "step": 190
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018905322006875617,
      "loss": 0.7997,
      "step": 191
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001889342148882519,
      "loss": 0.7553,
      "step": 192
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001888146042060005,
      "loss": 0.8128,
      "step": 193
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018869438883636214,
      "loss": 0.8158,
      "step": 194
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018857356959781378,
      "loss": 0.8029,
      "step": 195
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000188452147312944,
      "loss": 0.788,
      "step": 196
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018833012280844699,
      "loss": 0.785,
      "step": 197
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001882074969151172,
      "loss": 0.7955,
      "step": 198
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018808427046784366,
      "loss": 0.8033,
      "step": 199
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000187960444305604,
      "loss": 0.7744,
      "step": 200
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001878360192714592,
      "loss": 0.8084,
      "step": 201
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018771099621254746,
      "loss": 0.8271,
      "step": 202
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018758537598007868,
      "loss": 0.8153,
      "step": 203
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001874591594293285,
      "loss": 0.7638,
      "step": 204
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001873323474196326,
      "loss": 0.7825,
      "step": 205
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00018720494081438078,
      "loss": 0.7939,
      "step": 206
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00018707694048101104,
      "loss": 0.8289,
      "step": 207
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00018694834729100386,
      "loss": 0.7978,
      "step": 208
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00018681916211987597,
      "loss": 0.7921,
      "step": 209
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018668938584717471,
      "loss": 0.7849,
      "step": 210
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018655901935647187,
      "loss": 0.7512,
      "step": 211
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018642806353535754,
      "loss": 0.7452,
      "step": 212
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018629651927543447,
      "loss": 0.7714,
      "step": 213
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018616438747231148,
      "loss": 0.7974,
      "step": 214
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00018603166902559783,
      "loss": 0.7938,
      "step": 215
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018589836483889687,
      "loss": 0.7861,
      "step": 216
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018576447581979984,
      "loss": 0.7472,
      "step": 217
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001856300028798798,
      "loss": 0.7789,
      "step": 218
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001854949469346854,
      "loss": 0.7047,
      "step": 219
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018535930890373466,
      "loss": 0.7304,
      "step": 220
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018522308971050865,
      "loss": 0.7701,
      "step": 221
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018508629028244519,
      "loss": 0.8023,
      "step": 222
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018494891155093274,
      "loss": 0.8144,
      "step": 223
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001848109544513037,
      "loss": 0.7951,
      "step": 224
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018467241992282843,
      "loss": 0.7478,
      "step": 225
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018453330890870855,
      "loss": 0.8309,
      "step": 226
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001843936223560707,
      "loss": 0.7643,
      "step": 227
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018425336121596,
      "loss": 0.7689,
      "step": 228
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018411252644333362,
      "loss": 0.7866,
      "step": 229
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018397111899705419,
      "loss": 0.7165,
      "step": 230
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018382913983988348,
      "loss": 0.8189,
      "step": 231
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018368658993847566,
      "loss": 0.7934,
      "step": 232
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018354347026337066,
      "loss": 0.7668,
      "step": 233
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001833997817889878,
      "loss": 0.7278,
      "step": 234
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000183255525493619,
      "loss": 0.7661,
      "step": 235
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001831107023594221,
      "loss": 0.8165,
      "step": 236
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018296531337241425,
      "loss": 0.8411,
      "step": 237
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018281935952246518,
      "loss": 0.7806,
      "step": 238
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001826728418032904,
      "loss": 0.7821,
      "step": 239
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018252576121244456,
      "loss": 0.7878,
      "step": 240
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018237811875131444,
      "loss": 0.7586,
      "step": 241
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018222991542511246,
      "loss": 0.7855,
      "step": 242
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018208115224286947,
      "loss": 0.7881,
      "step": 243
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001819318302174281,
      "loss": 0.7394,
      "step": 244
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018178195036543592,
      "loss": 0.7526,
      "step": 245
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018163151370733838,
      "loss": 0.7969,
      "step": 246
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018148052126737177,
      "loss": 0.7877,
      "step": 247
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018132897407355657,
      "loss": 0.7849,
      "step": 248
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018117687315769007,
      "loss": 0.7871,
      "step": 249
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018102421955533974,
      "loss": 0.7423,
      "step": 250
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018087101430583577,
      "loss": 0.7658,
      "step": 251
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00018071725845226436,
      "loss": 0.7778,
      "step": 252
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001805629530414604,
      "loss": 0.7429,
      "step": 253
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001804080991240003,
      "loss": 0.7622,
      "step": 254
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00018025269775419507,
      "loss": 0.8222,
      "step": 255
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000180096749990083,
      "loss": 0.7611,
      "step": 256
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017994025689342235,
      "loss": 0.7496,
      "step": 257
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017978321952968434,
      "loss": 0.7821,
      "step": 258
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017962563896804578,
      "loss": 0.732,
      "step": 259
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017946751628138174,
      "loss": 0.7608,
      "step": 260
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017930885254625832,
      "loss": 0.7711,
      "step": 261
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017914964884292544,
      "loss": 0.769,
      "step": 262
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001789899062553091,
      "loss": 0.7177,
      "step": 263
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001788296258710045,
      "loss": 0.7931,
      "step": 264
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017866880878126824,
      "loss": 0.745,
      "step": 265
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001785074560810111,
      "loss": 0.8056,
      "step": 266
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017834556886879045,
      "loss": 0.7687,
      "step": 267
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000178183148246803,
      "loss": 0.7665,
      "step": 268
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017802019532087694,
      "loss": 0.7694,
      "step": 269
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017785671120046473,
      "loss": 0.7823,
      "step": 270
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017769269699863542,
      "loss": 0.7712,
      "step": 271
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017752815383206705,
      "loss": 0.7356,
      "step": 272
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017736308282103908,
      "loss": 0.7644,
      "step": 273
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001771974850894248,
      "loss": 0.7623,
      "step": 274
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017703136176468355,
      "loss": 0.7771,
      "step": 275
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001768647139778532,
      "loss": 0.832,
      "step": 276
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017669754286354241,
      "loss": 0.7733,
      "step": 277
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017652984955992277,
      "loss": 0.7669,
      "step": 278
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017636163520872122,
      "loss": 0.8019,
      "step": 279
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001761929009552122,
      "loss": 0.7812,
      "step": 280
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001760236479482099,
      "loss": 0.7761,
      "step": 281
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017585387734006034,
      "loss": 0.835,
      "step": 282
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017568359028663364,
      "loss": 0.7895,
      "step": 283
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017551278794731607,
      "loss": 0.7483,
      "step": 284
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001753414714850022,
      "loss": 0.7672,
      "step": 285
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017516964206608696,
      "loss": 0.777,
      "step": 286
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017499730086045767,
      "loss": 0.8055,
      "step": 287
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017482444904148617,
      "loss": 0.7941,
      "step": 288
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001746510877860208,
      "loss": 0.7886,
      "step": 289
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001744772182743782,
      "loss": 0.7651,
      "step": 290
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001743028416903356,
      "loss": 0.7244,
      "step": 291
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017412795922112253,
      "loss": 0.7792,
      "step": 292
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001739525720574128,
      "loss": 0.7187,
      "step": 293
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001737766813933164,
      "loss": 0.7578,
      "step": 294
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001736002884263713,
      "loss": 0.7841,
      "step": 295
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017342339435753553,
      "loss": 0.7706,
      "step": 296
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017324600039117863,
      "loss": 0.7369,
      "step": 297
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017306810773507376,
      "loss": 0.7624,
      "step": 298
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017288971760038942,
      "loss": 0.7672,
      "step": 299
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017271083120168102,
      "loss": 0.7777,
      "step": 300
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017253144975688285,
      "loss": 0.7862,
      "step": 301
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017235157448729967,
      "loss": 0.7499,
      "step": 302
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017217120661759832,
      "loss": 0.7255,
      "step": 303
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001719903473757996,
      "loss": 0.7993,
      "step": 304
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.7903943061828613,
      "eval_runtime": 85.3888,
      "eval_samples_per_second": 4.029,
      "eval_steps_per_second": 2.014,
      "step": 304
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001718089979932697,
      "loss": 0.7813,
      "step": 305
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001716271597047119,
      "loss": 0.7613,
      "step": 306
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001714448337481582,
      "loss": 0.7356,
      "step": 307
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001712620213649608,
      "loss": 0.7831,
      "step": 308
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017107872379978374,
      "loss": 0.7554,
      "step": 309
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017089494230059432,
      "loss": 0.7791,
      "step": 310
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.7561,
      "step": 311
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001705259325085135,
      "loss": 0.7705,
      "step": 312
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00017034070672799684,
      "loss": 0.7968,
      "step": 313
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00017015500203820022,
      "loss": 0.7709,
      "step": 314
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016996881970347962,
      "loss": 0.7818,
      "step": 315
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001697821609914432,
      "loss": 0.8448,
      "step": 316
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016959502717294242,
      "loss": 0.7488,
      "step": 317
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001694074195220634,
      "loss": 0.795,
      "step": 318
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001692193393161184,
      "loss": 0.8145,
      "step": 319
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000169030787835637,
      "loss": 0.7788,
      "step": 320
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016884176636435748,
      "loss": 0.7627,
      "step": 321
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016865227618921788,
      "loss": 0.7744,
      "step": 322
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016846231860034747,
      "loss": 0.7998,
      "step": 323
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016827189489105788,
      "loss": 0.779,
      "step": 324
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016808100635783423,
      "loss": 0.7434,
      "step": 325
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016788965430032638,
      "loss": 0.717,
      "step": 326
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016769784002134008,
      "loss": 0.729,
      "step": 327
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016750556482682805,
      "loss": 0.7918,
      "step": 328
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001673128300258812,
      "loss": 0.77,
      "step": 329
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016711963693071943,
      "loss": 0.8369,
      "step": 330
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016692598685668318,
      "loss": 0.8058,
      "step": 331
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016673188112222394,
      "loss": 0.7752,
      "step": 332
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016653732104889572,
      "loss": 0.728,
      "step": 333
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016634230796134576,
      "loss": 0.7681,
      "step": 334
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001661468431873056,
      "loss": 0.7822,
      "step": 335
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001659509280575821,
      "loss": 0.766,
      "step": 336
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001657545639060484,
      "loss": 0.7927,
      "step": 337
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001655577520696346,
      "loss": 0.7923,
      "step": 338
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016536049388831894,
      "loss": 0.7688,
      "step": 339
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016516279070511854,
      "loss": 0.7411,
      "step": 340
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001649646438660803,
      "loss": 0.777,
      "step": 341
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016476605472027172,
      "loss": 0.8018,
      "step": 342
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001645670246197716,
      "loss": 0.7639,
      "step": 343
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016436755491966115,
      "loss": 0.7529,
      "step": 344
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016416764697801438,
      "loss": 0.7715,
      "step": 345
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016396730215588915,
      "loss": 0.7675,
      "step": 346
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016376652181731769,
      "loss": 0.7334,
      "step": 347
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001635653073292975,
      "loss": 0.8244,
      "step": 348
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016336366006178187,
      "loss": 0.7749,
      "step": 349
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001631615813876707,
      "loss": 0.7767,
      "step": 350
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016295907268280109,
      "loss": 0.7952,
      "step": 351
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001627561353259379,
      "loss": 0.7624,
      "step": 352
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016255277069876454,
      "loss": 0.7682,
      "step": 353
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.7176,
      "step": 354
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016214476517475637,
      "loss": 0.7674,
      "step": 355
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016194012705579572,
      "loss": 0.8107,
      "step": 356
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016173506722225428,
      "loss": 0.7778,
      "step": 357
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016152958707026614,
      "loss": 0.7688,
      "step": 358
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016132368799882704,
      "loss": 0.7777,
      "step": 359
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016111737140978494,
      "loss": 0.7688,
      "step": 360
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016091063870783047,
      "loss": 0.737,
      "step": 361
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016070349130048724,
      "loss": 0.7176,
      "step": 362
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016049593059810248,
      "loss": 0.773,
      "step": 363
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016028795801383718,
      "loss": 0.7305,
      "step": 364
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016007957496365667,
      "loss": 0.7872,
      "step": 365
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001598707828663209,
      "loss": 0.764,
      "step": 366
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00015966158314337472,
      "loss": 0.765,
      "step": 367
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015945197721913833,
      "loss": 0.7292,
      "step": 368
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015924196652069758,
      "loss": 0.7311,
      "step": 369
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015903155247789404,
      "loss": 0.8094,
      "step": 370
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015882073652331556,
      "loss": 0.7841,
      "step": 371
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015860952009228625,
      "loss": 0.7609,
      "step": 372
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015839790462285696,
      "loss": 0.7436,
      "step": 373
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001581858915557953,
      "loss": 0.8029,
      "step": 374
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015797348233457584,
      "loss": 0.7918,
      "step": 375
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001577606784053705,
      "loss": 0.759,
      "step": 376
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001575474812170383,
      "loss": 0.7535,
      "step": 377
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015733389222111592,
      "loss": 0.7787,
      "step": 378
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001571199128718076,
      "loss": 0.7767,
      "step": 379
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015690554462597522,
      "loss": 0.7664,
      "step": 380
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015669078894312848,
      "loss": 0.784,
      "step": 381
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015647564728541485,
      "loss": 0.7815,
      "step": 382
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015626012111760975,
      "loss": 0.7598,
      "step": 383
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001560442119071065,
      "loss": 0.7546,
      "step": 384
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001558279211239063,
      "loss": 0.7328,
      "step": 385
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015561125024060826,
      "loss": 0.7731,
      "step": 386
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015539420073239942,
      "loss": 0.8272,
      "step": 387
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001551767740770446,
      "loss": 0.7338,
      "step": 388
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015495897175487645,
      "loss": 0.7247,
      "step": 389
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015474079524878525,
      "loss": 0.796,
      "step": 390
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015452224604420897,
      "loss": 0.8094,
      "step": 391
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000154303325629123,
      "loss": 0.768,
      "step": 392
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001540840354940301,
      "loss": 0.8052,
      "step": 393
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001538643771319503,
      "loss": 0.7602,
      "step": 394
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015364435203841058,
      "loss": 0.8005,
      "step": 395
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015342396171143488,
      "loss": 0.7279,
      "step": 396
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015320320765153367,
      "loss": 0.7832,
      "step": 397
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015298209136169403,
      "loss": 0.7498,
      "step": 398
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015276061434736914,
      "loss": 0.7825,
      "step": 399
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015253877811646817,
      "loss": 0.7973,
      "step": 400
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015231658417934606,
      "loss": 0.724,
      "step": 401
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015209403404879303,
      "loss": 0.7573,
      "step": 402
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015187112924002456,
      "loss": 0.7406,
      "step": 403
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001516478712706708,
      "loss": 0.7326,
      "step": 404
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015142426166076645,
      "loss": 0.764,
      "step": 405
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015120030193274027,
      "loss": 0.6982,
      "step": 406
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015097599361140487,
      "loss": 0.7991,
      "step": 407
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015075133822394613,
      "loss": 0.7592,
      "step": 408
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015052633729991294,
      "loss": 0.7671,
      "step": 409
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015030099237120674,
      "loss": 0.7908,
      "step": 410
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015007530497207117,
      "loss": 0.7631,
      "step": 411
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00014984927663908137,
      "loss": 0.73,
      "step": 412
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00014962290891113394,
      "loss": 0.7648,
      "step": 413
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00014939620332943604,
      "loss": 0.7777,
      "step": 414
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00014916916143749518,
      "loss": 0.7699,
      "step": 415
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014894178478110857,
      "loss": 0.7755,
      "step": 416
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014871407490835262,
      "loss": 0.7863,
      "step": 417
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014848603336957251,
      "loss": 0.7413,
      "step": 418
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014825766171737146,
      "loss": 0.7917,
      "step": 419
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014802896150660022,
      "loss": 0.7522,
      "step": 420
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00014779993429434659,
      "loss": 0.7361,
      "step": 421
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00014757058163992464,
      "loss": 0.7713,
      "step": 422
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00014734090510486433,
      "loss": 0.7535,
      "step": 423
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00014711090625290057,
      "loss": 0.7542,
      "step": 424
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00014688058664996285,
      "loss": 0.7781,
      "step": 425
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001466499478641644,
      "loss": 0.7643,
      "step": 426
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00014641899146579168,
      "loss": 0.7743,
      "step": 427
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014618771902729342,
      "loss": 0.7716,
      "step": 428
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014595613212327032,
      "loss": 0.7737,
      "step": 429
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014572423233046386,
      "loss": 0.8296,
      "step": 430
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014549202122774596,
      "loss": 0.771,
      "step": 431
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000145259500396108,
      "loss": 0.7118,
      "step": 432
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014502667141865015,
      "loss": 0.7397,
      "step": 433
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00014479353588057052,
      "loss": 0.7823,
      "step": 434
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014456009536915448,
      "loss": 0.7566,
      "step": 435
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014432635147376376,
      "loss": 0.7891,
      "step": 436
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014409230578582566,
      "loss": 0.7022,
      "step": 437
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014385795989882221,
      "loss": 0.75,
      "step": 438
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014362331540827928,
      "loss": 0.7041,
      "step": 439
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014338837391175582,
      "loss": 0.794,
      "step": 440
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00014315313700883294,
      "loss": 0.7303,
      "step": 441
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00014291760630110288,
      "loss": 0.7824,
      "step": 442
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00014268178339215838,
      "loss": 0.7425,
      "step": 443
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00014244566988758152,
      "loss": 0.7322,
      "step": 444
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00014220926739493288,
      "loss": 0.7444,
      "step": 445
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001419725775237406,
      "loss": 0.7536,
      "step": 446
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00014173560188548948,
      "loss": 0.7671,
      "step": 447
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00014149834209360986,
      "loss": 0.7207,
      "step": 448
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001412607997634667,
      "loss": 0.7493,
      "step": 449
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001410229765123487,
      "loss": 0.7515,
      "step": 450
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00014078487395945713,
      "loss": 0.7984,
      "step": 451
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00014054649372589482,
      "loss": 0.7558,
      "step": 452
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00014030783743465528,
      "loss": 0.7545,
      "step": 453
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00014006890671061143,
      "loss": 0.7613,
      "step": 454
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001398297031805047,
      "loss": 0.7827,
      "step": 455
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00013959022847293391,
      "loss": 0.7348,
      "step": 456
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.7748340368270874,
      "eval_runtime": 85.3906,
      "eval_samples_per_second": 4.029,
      "eval_steps_per_second": 2.014,
      "step": 456
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001393504842183441,
      "loss": 0.8026,
      "step": 457
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001391104720490156,
      "loss": 0.7807,
      "step": 458
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00013887019359905275,
      "loss": 0.7578,
      "step": 459
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001386296505043728,
      "loss": 0.7462,
      "step": 460
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00013838884440269496,
      "loss": 0.7644,
      "step": 461
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000138147776933529,
      "loss": 0.7897,
      "step": 462
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001379064497381641,
      "loss": 0.7399,
      "step": 463
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00013766486445965795,
      "loss": 0.767,
      "step": 464
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00013742302274282533,
      "loss": 0.7733,
      "step": 465
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00013718092623422686,
      "loss": 0.7551,
      "step": 466
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000136938576582158,
      "loss": 0.7815,
      "step": 467
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00013669597543663762,
      "loss": 0.74,
      "step": 468
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000136453124449397,
      "loss": 0.7374,
      "step": 469
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00013621002527386834,
      "loss": 0.741,
      "step": 470
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001359666795651736,
      "loss": 0.7938,
      "step": 471
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001357230889801133,
      "loss": 0.7252,
      "step": 472
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00013547925517715519,
      "loss": 0.7318,
      "step": 473
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00013523517981642286,
      "loss": 0.741,
      "step": 474
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00013499086455968467,
      "loss": 0.7595,
      "step": 475
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001347463110703422,
      "loss": 0.7767,
      "step": 476
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013450152101341896,
      "loss": 0.7698,
      "step": 477
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013425649605554928,
      "loss": 0.7661,
      "step": 478
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013401123786496664,
      "loss": 0.7558,
      "step": 479
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013376574811149253,
      "loss": 0.745,
      "step": 480
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013352002846652504,
      "loss": 0.7501,
      "step": 481
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013327408060302738,
      "loss": 0.7399,
      "step": 482
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013302790619551674,
      "loss": 0.7038,
      "step": 483
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013278150692005243,
      "loss": 0.7526,
      "step": 484
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013253488445422507,
      "loss": 0.7493,
      "step": 485
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013228804047714463,
      "loss": 0.7053,
      "step": 486
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013204097666942932,
      "loss": 0.7826,
      "step": 487
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013179369471319404,
      "loss": 0.7719,
      "step": 488
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00013154619629203893,
      "loss": 0.7668,
      "step": 489
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001312984830910379,
      "loss": 0.762,
      "step": 490
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001310505567967272,
      "loss": 0.7346,
      "step": 491
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00013080241909709387,
      "loss": 0.7595,
      "step": 492
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00013055407168156437,
      "loss": 0.7422,
      "step": 493
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00013030551624099287,
      "loss": 0.7342,
      "step": 494
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00013005675446764998,
      "loss": 0.7401,
      "step": 495
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000129807788055211,
      "loss": 0.7577,
      "step": 496
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001295586186987446,
      "loss": 0.7662,
      "step": 497
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00012930924809470115,
      "loss": 0.7131,
      "step": 498
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00012905967794090114,
      "loss": 0.7217,
      "step": 499
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00012880990993652377,
      "loss": 0.7616,
      "step": 500
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012855994578209526,
      "loss": 0.7784,
      "step": 501
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012830978717947718,
      "loss": 0.7677,
      "step": 502
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012805943583185525,
      "loss": 0.7629,
      "step": 503
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012780889344372718,
      "loss": 0.7648,
      "step": 504
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012755816172089164,
      "loss": 0.785,
      "step": 505
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012730724237043615,
      "loss": 0.7422,
      "step": 506
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012705613710072575,
      "loss": 0.7862,
      "step": 507
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001268048476213914,
      "loss": 0.7736,
      "step": 508
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012655337564331805,
      "loss": 0.7511,
      "step": 509
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001263017228786334,
      "loss": 0.7707,
      "step": 510
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001260498910406958,
      "loss": 0.7744,
      "step": 511
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012579788184408295,
      "loss": 0.7391,
      "step": 512
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012554569700458002,
      "loss": 0.6762,
      "step": 513
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012529333823916807,
      "loss": 0.7606,
      "step": 514
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012504080726601232,
      "loss": 0.7928,
      "step": 515
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001247881058044504,
      "loss": 0.7404,
      "step": 516
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012453523557498075,
      "loss": 0.7493,
      "step": 517
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012428219829925083,
      "loss": 0.7582,
      "step": 518
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00012402899570004543,
      "loss": 0.7012,
      "step": 519
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00012377562950127493,
      "loss": 0.7698,
      "step": 520
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001235221014279636,
      "loss": 0.7408,
      "step": 521
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00012326841320623767,
      "loss": 0.7724,
      "step": 522
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00012301456656331402,
      "loss": 0.7512,
      "step": 523
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00012276056322748778,
      "loss": 0.7509,
      "step": 524
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001225064049281212,
      "loss": 0.7561,
      "step": 525
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.7758,
      "step": 526
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012199763036147895,
      "loss": 0.8028,
      "step": 527
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012174301755815571,
      "loss": 0.7113,
      "step": 528
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012148825671917334,
      "loss": 0.7941,
      "step": 529
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001212333495790514,
      "loss": 0.7639,
      "step": 530
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012097829787330544,
      "loss": 0.7481,
      "step": 531
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00012072310333843544,
      "loss": 0.7732,
      "step": 532
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00012046776771191366,
      "loss": 0.7493,
      "step": 533
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00012021229273217302,
      "loss": 0.7359,
      "step": 534
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00011995668013859529,
      "loss": 0.7319,
      "step": 535
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00011970093167149905,
      "loss": 0.7671,
      "step": 536
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00011944504907212804,
      "loss": 0.7514,
      "step": 537
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011918903408263924,
      "loss": 0.7095,
      "step": 538
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011893288844609094,
      "loss": 0.7625,
      "step": 539
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000118676613906431,
      "loss": 0.7346,
      "step": 540
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011842021220848486,
      "loss": 0.7206,
      "step": 541
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011816368509794364,
      "loss": 0.7408,
      "step": 542
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011790703432135253,
      "loss": 0.7213,
      "step": 543
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011765026162609847,
      "loss": 0.7476,
      "step": 544
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011739336876039859,
      "loss": 0.7787,
      "step": 545
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011713635747328818,
      "loss": 0.7646,
      "step": 546
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011687922951460872,
      "loss": 0.6935,
      "step": 547
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011662198663499619,
      "loss": 0.7403,
      "step": 548
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011636463058586881,
      "loss": 0.804,
      "step": 549
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001161071631194155,
      "loss": 0.7442,
      "step": 550
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011584958598858359,
      "loss": 0.76,
      "step": 551
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011559190094706714,
      "loss": 0.7403,
      "step": 552
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001153341097492949,
      "loss": 0.7514,
      "step": 553
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011507621415041837,
      "loss": 0.7438,
      "step": 554
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011481821590629985,
      "loss": 0.725,
      "step": 555
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011456011677350051,
      "loss": 0.6918,
      "step": 556
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011430191850926837,
      "loss": 0.767,
      "step": 557
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011404362287152646,
      "loss": 0.7356,
      "step": 558
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011378523161886066,
      "loss": 0.7281,
      "step": 559
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011352674651050796,
      "loss": 0.7428,
      "step": 560
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011326816930634427,
      "loss": 0.7005,
      "step": 561
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011300950176687255,
      "loss": 0.7109,
      "step": 562
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001127507456532108,
      "loss": 0.7378,
      "step": 563
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011249190272708008,
      "loss": 0.7413,
      "step": 564
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011223297475079251,
      "loss": 0.7741,
      "step": 565
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011197396348723923,
      "loss": 0.7547,
      "step": 566
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011171487069987851,
      "loss": 0.7478,
      "step": 567
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001114556981527236,
      "loss": 0.7138,
      "step": 568
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011119644761033078,
      "loss": 0.76,
      "step": 569
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011093712083778746,
      "loss": 0.771,
      "step": 570
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011067771960069991,
      "loss": 0.765,
      "step": 571
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011041824566518146,
      "loss": 0.7886,
      "step": 572
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011015870079784048,
      "loss": 0.7134,
      "step": 573
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010989908676576807,
      "loss": 0.7173,
      "step": 574
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010963940533652648,
      "loss": 0.7522,
      "step": 575
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010937965827813661,
      "loss": 0.7523,
      "step": 576
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010911984735906635,
      "loss": 0.7446,
      "step": 577
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010885997434821831,
      "loss": 0.7226,
      "step": 578
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010860004101491779,
      "loss": 0.7181,
      "step": 579
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010834004912890092,
      "loss": 0.7689,
      "step": 580
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001080800004603024,
      "loss": 0.7329,
      "step": 581
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010781989677964355,
      "loss": 0.7067,
      "step": 582
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010755973985782022,
      "loss": 0.7191,
      "step": 583
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010729953146609076,
      "loss": 0.716,
      "step": 584
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010703927337606396,
      "loss": 0.71,
      "step": 585
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010677896735968693,
      "loss": 0.7327,
      "step": 586
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010651861518923319,
      "loss": 0.7322,
      "step": 587
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010625821863729036,
      "loss": 0.7429,
      "step": 588
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010599777947674829,
      "loss": 0.7499,
      "step": 589
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010573729948078699,
      "loss": 0.7391,
      "step": 590
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010547678042286436,
      "loss": 0.7499,
      "step": 591
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010521622407670439,
      "loss": 0.7398,
      "step": 592
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010495563221628486,
      "loss": 0.7206,
      "step": 593
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010469500661582536,
      "loss": 0.7797,
      "step": 594
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010443434904977518,
      "loss": 0.7936,
      "step": 595
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010417366129280133,
      "loss": 0.7512,
      "step": 596
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00010391294511977623,
      "loss": 0.7616,
      "step": 597
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001036522023057659,
      "loss": 0.7767,
      "step": 598
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010339143462601768,
      "loss": 0.7676,
      "step": 599
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010313064385594822,
      "loss": 0.7357,
      "step": 600
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010286983177113135,
      "loss": 0.7563,
      "step": 601
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001026090001472861,
      "loss": 0.7228,
      "step": 602
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010234815076026442,
      "loss": 0.7603,
      "step": 603
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00010208728538603929,
      "loss": 0.7354,
      "step": 604
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001018264058006925,
      "loss": 0.7657,
      "step": 605
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00010156551378040258,
      "loss": 0.7103,
      "step": 606
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00010130461110143277,
      "loss": 0.7663,
      "step": 607
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00010104369954011883,
      "loss": 0.689,
      "step": 608
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7638368010520935,
      "eval_runtime": 85.3956,
      "eval_samples_per_second": 4.028,
      "eval_steps_per_second": 2.014,
      "step": 608
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.000100782780872857,
      "loss": 0.7185,
      "step": 609
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00010052185687609197,
      "loss": 0.7591,
      "step": 610
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00010026092932630457,
      "loss": 0.7321,
      "step": 611
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001,
      "loss": 0.6723,
      "step": 612
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.973907067369543e-05,
      "loss": 0.73,
      "step": 613
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.947814312390808e-05,
      "loss": 0.7105,
      "step": 614
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.921721912714301e-05,
      "loss": 0.7369,
      "step": 615
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.89563004598812e-05,
      "loss": 0.7216,
      "step": 616
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.869538889856723e-05,
      "loss": 0.7139,
      "step": 617
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.843448621959745e-05,
      "loss": 0.834,
      "step": 618
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.817359419930751e-05,
      "loss": 0.6715,
      "step": 619
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.79127146139607e-05,
      "loss": 0.6705,
      "step": 620
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.765184923973561e-05,
      "loss": 0.6373,
      "step": 621
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.739099985271394e-05,
      "loss": 0.5946,
      "step": 622
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.713016822886866e-05,
      "loss": 0.6371,
      "step": 623
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.686935614405183e-05,
      "loss": 0.6413,
      "step": 624
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.660856537398235e-05,
      "loss": 0.6573,
      "step": 625
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.63477976942341e-05,
      "loss": 0.6552,
      "step": 626
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.608705488022378e-05,
      "loss": 0.6071,
      "step": 627
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.582633870719871e-05,
      "loss": 0.5831,
      "step": 628
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.556565095022483e-05,
      "loss": 0.6384,
      "step": 629
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.530499338417465e-05,
      "loss": 0.6526,
      "step": 630
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.504436778371515e-05,
      "loss": 0.6406,
      "step": 631
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.478377592329563e-05,
      "loss": 0.6576,
      "step": 632
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.452321957713564e-05,
      "loss": 0.5921,
      "step": 633
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.426270051921304e-05,
      "loss": 0.6291,
      "step": 634
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.400222052325174e-05,
      "loss": 0.6031,
      "step": 635
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.374178136270966e-05,
      "loss": 0.6253,
      "step": 636
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.348138481076682e-05,
      "loss": 0.6057,
      "step": 637
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.32210326403131e-05,
      "loss": 0.5977,
      "step": 638
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.296072662393607e-05,
      "loss": 0.5896,
      "step": 639
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.270046853390925e-05,
      "loss": 0.665,
      "step": 640
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.244026014217981e-05,
      "loss": 0.6332,
      "step": 641
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.218010322035647e-05,
      "loss": 0.6381,
      "step": 642
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.19199995396976e-05,
      "loss": 0.6296,
      "step": 643
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.165995087109911e-05,
      "loss": 0.6414,
      "step": 644
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.139995898508223e-05,
      "loss": 0.6394,
      "step": 645
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.114002565178172e-05,
      "loss": 0.616,
      "step": 646
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.088015264093365e-05,
      "loss": 0.6024,
      "step": 647
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.062034172186341e-05,
      "loss": 0.555,
      "step": 648
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.036059466347354e-05,
      "loss": 0.6068,
      "step": 649
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.010091323423192e-05,
      "loss": 0.6503,
      "step": 650
    },
    {
      "epoch": 1.05,
      "learning_rate": 8.984129920215959e-05,
      "loss": 0.6535,
      "step": 651
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.958175433481855e-05,
      "loss": 0.5994,
      "step": 652
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.93222803993001e-05,
      "loss": 0.6477,
      "step": 653
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.906287916221259e-05,
      "loss": 0.6428,
      "step": 654
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.880355238966923e-05,
      "loss": 0.6173,
      "step": 655
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.85443018472764e-05,
      "loss": 0.602,
      "step": 656
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.82851293001215e-05,
      "loss": 0.619,
      "step": 657
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.802603651276078e-05,
      "loss": 0.6061,
      "step": 658
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.77670252492075e-05,
      "loss": 0.6148,
      "step": 659
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.750809727291995e-05,
      "loss": 0.6271,
      "step": 660
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.724925434678923e-05,
      "loss": 0.6758,
      "step": 661
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.699049823312748e-05,
      "loss": 0.5878,
      "step": 662
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.673183069365574e-05,
      "loss": 0.6095,
      "step": 663
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.647325348949206e-05,
      "loss": 0.6144,
      "step": 664
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.621476838113937e-05,
      "loss": 0.6126,
      "step": 665
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.595637712847358e-05,
      "loss": 0.6388,
      "step": 666
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.569808149073163e-05,
      "loss": 0.6338,
      "step": 667
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.543988322649954e-05,
      "loss": 0.6075,
      "step": 668
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.518178409370017e-05,
      "loss": 0.6488,
      "step": 669
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.492378584958164e-05,
      "loss": 0.6447,
      "step": 670
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.466589025070513e-05,
      "loss": 0.6006,
      "step": 671
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.440809905293288e-05,
      "loss": 0.6096,
      "step": 672
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.415041401141642e-05,
      "loss": 0.6107,
      "step": 673
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.389283688058454e-05,
      "loss": 0.6459,
      "step": 674
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.363536941413121e-05,
      "loss": 0.6209,
      "step": 675
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.337801336500383e-05,
      "loss": 0.6145,
      "step": 676
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.312077048539126e-05,
      "loss": 0.6321,
      "step": 677
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.286364252671187e-05,
      "loss": 0.6276,
      "step": 678
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.260663123960143e-05,
      "loss": 0.6188,
      "step": 679
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.234973837390154e-05,
      "loss": 0.6622,
      "step": 680
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.209296567864752e-05,
      "loss": 0.6904,
      "step": 681
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.183631490205637e-05,
      "loss": 0.7122,
      "step": 682
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.157978779151518e-05,
      "loss": 0.5989,
      "step": 683
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.132338609356904e-05,
      "loss": 0.6422,
      "step": 684
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.106711155390908e-05,
      "loss": 0.634,
      "step": 685
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.081096591736076e-05,
      "loss": 0.6079,
      "step": 686
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.055495092787196e-05,
      "loss": 0.612,
      "step": 687
    },
    {
      "epoch": 1.12,
      "learning_rate": 8.029906832850098e-05,
      "loss": 0.6142,
      "step": 688
    },
    {
      "epoch": 1.12,
      "learning_rate": 8.004331986140474e-05,
      "loss": 0.6485,
      "step": 689
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.978770726782697e-05,
      "loss": 0.6366,
      "step": 690
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.953223228808639e-05,
      "loss": 0.5951,
      "step": 691
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.927689666156458e-05,
      "loss": 0.6565,
      "step": 692
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.902170212669457e-05,
      "loss": 0.6055,
      "step": 693
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.876665042094867e-05,
      "loss": 0.618,
      "step": 694
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.851174328082669e-05,
      "loss": 0.6031,
      "step": 695
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.825698244184431e-05,
      "loss": 0.6288,
      "step": 696
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.800236963852106e-05,
      "loss": 0.6021,
      "step": 697
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.6174,
      "step": 698
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.749359507187882e-05,
      "loss": 0.6239,
      "step": 699
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.723943677251222e-05,
      "loss": 0.5647,
      "step": 700
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.698543343668602e-05,
      "loss": 0.631,
      "step": 701
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.673158679376234e-05,
      "loss": 0.616,
      "step": 702
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.647789857203645e-05,
      "loss": 0.6188,
      "step": 703
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.622437049872512e-05,
      "loss": 0.6081,
      "step": 704
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.59710042999546e-05,
      "loss": 0.6027,
      "step": 705
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.57178017007492e-05,
      "loss": 0.5911,
      "step": 706
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.546476442501926e-05,
      "loss": 0.6203,
      "step": 707
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.521189419554963e-05,
      "loss": 0.6708,
      "step": 708
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.49591927339877e-05,
      "loss": 0.6208,
      "step": 709
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.470666176083192e-05,
      "loss": 0.6666,
      "step": 710
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.445430299542002e-05,
      "loss": 0.5954,
      "step": 711
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.420211815591709e-05,
      "loss": 0.6534,
      "step": 712
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.395010895930421e-05,
      "loss": 0.6602,
      "step": 713
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.369827712136661e-05,
      "loss": 0.5965,
      "step": 714
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.344662435668196e-05,
      "loss": 0.6035,
      "step": 715
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.319515237860864e-05,
      "loss": 0.6415,
      "step": 716
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.294386289927425e-05,
      "loss": 0.6269,
      "step": 717
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.269275762956392e-05,
      "loss": 0.6435,
      "step": 718
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.24418382791084e-05,
      "loss": 0.5906,
      "step": 719
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.219110655627281e-05,
      "loss": 0.6357,
      "step": 720
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.194056416814481e-05,
      "loss": 0.649,
      "step": 721
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.169021282052283e-05,
      "loss": 0.6298,
      "step": 722
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.144005421790479e-05,
      "loss": 0.6458,
      "step": 723
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.119009006347625e-05,
      "loss": 0.6752,
      "step": 724
    },
    {
      "epoch": 1.18,
      "learning_rate": 7.094032205909888e-05,
      "loss": 0.6462,
      "step": 725
    },
    {
      "epoch": 1.18,
      "learning_rate": 7.069075190529888e-05,
      "loss": 0.6002,
      "step": 726
    },
    {
      "epoch": 1.18,
      "learning_rate": 7.044138130125542e-05,
      "loss": 0.6292,
      "step": 727
    },
    {
      "epoch": 1.18,
      "learning_rate": 7.019221194478904e-05,
      "loss": 0.634,
      "step": 728
    },
    {
      "epoch": 1.18,
      "learning_rate": 6.994324553235006e-05,
      "loss": 0.6157,
      "step": 729
    },
    {
      "epoch": 1.18,
      "learning_rate": 6.969448375900715e-05,
      "loss": 0.6334,
      "step": 730
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.944592831843566e-05,
      "loss": 0.6194,
      "step": 731
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.919758090290614e-05,
      "loss": 0.5901,
      "step": 732
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.894944320327281e-05,
      "loss": 0.6061,
      "step": 733
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.870151690896209e-05,
      "loss": 0.6211,
      "step": 734
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.845380370796111e-05,
      "loss": 0.6243,
      "step": 735
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.820630528680597e-05,
      "loss": 0.6249,
      "step": 736
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.795902333057067e-05,
      "loss": 0.6146,
      "step": 737
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.77119595228554e-05,
      "loss": 0.6207,
      "step": 738
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.746511554577497e-05,
      "loss": 0.62,
      "step": 739
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.721849307994756e-05,
      "loss": 0.6363,
      "step": 740
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.697209380448333e-05,
      "loss": 0.6056,
      "step": 741
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.672591939697261e-05,
      "loss": 0.6144,
      "step": 742
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.647997153347498e-05,
      "loss": 0.6448,
      "step": 743
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.623425188850746e-05,
      "loss": 0.6531,
      "step": 744
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.598876213503339e-05,
      "loss": 0.6569,
      "step": 745
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.574350394445074e-05,
      "loss": 0.5947,
      "step": 746
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.549847898658102e-05,
      "loss": 0.6203,
      "step": 747
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.525368892965784e-05,
      "loss": 0.6369,
      "step": 748
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.500913544031534e-05,
      "loss": 0.6199,
      "step": 749
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.476482018357713e-05,
      "loss": 0.6155,
      "step": 750
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.452074482284487e-05,
      "loss": 0.6311,
      "step": 751
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.427691101988673e-05,
      "loss": 0.6374,
      "step": 752
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.403332043482643e-05,
      "loss": 0.5893,
      "step": 753
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.378997472613169e-05,
      "loss": 0.6227,
      "step": 754
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.354687555060302e-05,
      "loss": 0.6444,
      "step": 755
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.330402456336237e-05,
      "loss": 0.583,
      "step": 756
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.306142341784202e-05,
      "loss": 0.6229,
      "step": 757
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.281907376577316e-05,
      "loss": 0.6414,
      "step": 758
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.257697725717468e-05,
      "loss": 0.6413,
      "step": 759
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.233513554034204e-05,
      "loss": 0.6462,
      "step": 760
    },
    {
      "epoch": 1.23,
      "eval_loss": 0.7729330658912659,
      "eval_runtime": 85.3449,
      "eval_samples_per_second": 4.031,
      "eval_steps_per_second": 2.015,
      "step": 760
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.209355026183594e-05,
      "loss": 0.6203,
      "step": 761
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.185222306647105e-05,
      "loss": 0.608,
      "step": 762
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.161115559730505e-05,
      "loss": 0.6313,
      "step": 763
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.137034949562719e-05,
      "loss": 0.64,
      "step": 764
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.112980640094728e-05,
      "loss": 0.6209,
      "step": 765
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.0889527950984416e-05,
      "loss": 0.6729,
      "step": 766
    },
    {
      "epoch": 1.25,
      "learning_rate": 6.06495157816559e-05,
      "loss": 0.5984,
      "step": 767
    },
    {
      "epoch": 1.25,
      "learning_rate": 6.040977152706613e-05,
      "loss": 0.5975,
      "step": 768
    },
    {
      "epoch": 1.25,
      "learning_rate": 6.017029681949531e-05,
      "loss": 0.5956,
      "step": 769
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.9931093289388576e-05,
      "loss": 0.5867,
      "step": 770
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.9692162565344755e-05,
      "loss": 0.6214,
      "step": 771
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.94535062741052e-05,
      "loss": 0.6309,
      "step": 772
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.921512604054289e-05,
      "loss": 0.618,
      "step": 773
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.897702348765129e-05,
      "loss": 0.6164,
      "step": 774
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.873920023653332e-05,
      "loss": 0.6114,
      "step": 775
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.8501657906390175e-05,
      "loss": 0.664,
      "step": 776
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.826439811451052e-05,
      "loss": 0.6307,
      "step": 777
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.8027422476259385e-05,
      "loss": 0.6208,
      "step": 778
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.779073260506713e-05,
      "loss": 0.6693,
      "step": 779
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.755433011241851e-05,
      "loss": 0.62,
      "step": 780
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.7318216607841644e-05,
      "loss": 0.6204,
      "step": 781
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.7082393698897166e-05,
      "loss": 0.5948,
      "step": 782
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.684686299116709e-05,
      "loss": 0.6278,
      "step": 783
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.617,
      "step": 784
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.6376684591720766e-05,
      "loss": 0.6114,
      "step": 785
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.614204010117785e-05,
      "loss": 0.6278,
      "step": 786
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.5907694214174344e-05,
      "loss": 0.6217,
      "step": 787
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.567364852623629e-05,
      "loss": 0.6272,
      "step": 788
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.543990463084554e-05,
      "loss": 0.6162,
      "step": 789
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.520646411942951e-05,
      "loss": 0.5987,
      "step": 790
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.497332858134992e-05,
      "loss": 0.6191,
      "step": 791
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.474049960389205e-05,
      "loss": 0.6137,
      "step": 792
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.450797877225404e-05,
      "loss": 0.6011,
      "step": 793
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.4275767669536146e-05,
      "loss": 0.6212,
      "step": 794
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.40438678767297e-05,
      "loss": 0.6065,
      "step": 795
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.381228097270659e-05,
      "loss": 0.6415,
      "step": 796
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.3581008534208334e-05,
      "loss": 0.6529,
      "step": 797
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.3350052135835616e-05,
      "loss": 0.6042,
      "step": 798
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.311941335003715e-05,
      "loss": 0.6675,
      "step": 799
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.2889093747099427e-05,
      "loss": 0.6439,
      "step": 800
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.265909489513567e-05,
      "loss": 0.6387,
      "step": 801
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.242941836007536e-05,
      "loss": 0.6259,
      "step": 802
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.220006570565341e-05,
      "loss": 0.6026,
      "step": 803
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.197103849339978e-05,
      "loss": 0.6114,
      "step": 804
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.174233828262855e-05,
      "loss": 0.6024,
      "step": 805
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.151396663042749e-05,
      "loss": 0.6046,
      "step": 806
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.128592509164736e-05,
      "loss": 0.6075,
      "step": 807
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.105821521889147e-05,
      "loss": 0.6151,
      "step": 808
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.0830838562504835e-05,
      "loss": 0.6032,
      "step": 809
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.060379667056399e-05,
      "loss": 0.6134,
      "step": 810
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.0377091088866094e-05,
      "loss": 0.6302,
      "step": 811
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.015072336091866e-05,
      "loss": 0.5702,
      "step": 812
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.992469502792889e-05,
      "loss": 0.5978,
      "step": 813
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.969900762879325e-05,
      "loss": 0.5971,
      "step": 814
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.947366270008707e-05,
      "loss": 0.6176,
      "step": 815
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.924866177605389e-05,
      "loss": 0.6262,
      "step": 816
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.9024006388595155e-05,
      "loss": 0.588,
      "step": 817
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.8799698067259757e-05,
      "loss": 0.6384,
      "step": 818
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.857573833923361e-05,
      "loss": 0.6002,
      "step": 819
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.8352128729329226e-05,
      "loss": 0.6147,
      "step": 820
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.8128870759975474e-05,
      "loss": 0.6516,
      "step": 821
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.790596595120699e-05,
      "loss": 0.6057,
      "step": 822
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.7683415820653976e-05,
      "loss": 0.5802,
      "step": 823
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.746122188353182e-05,
      "loss": 0.6236,
      "step": 824
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.723938565263091e-05,
      "loss": 0.5929,
      "step": 825
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.7017908638305995e-05,
      "loss": 0.6288,
      "step": 826
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.6796792348466356e-05,
      "loss": 0.6139,
      "step": 827
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.657603828856517e-05,
      "loss": 0.5989,
      "step": 828
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.635564796158945e-05,
      "loss": 0.6185,
      "step": 829
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.61356228680497e-05,
      "loss": 0.6254,
      "step": 830
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.59159645059699e-05,
      "loss": 0.5979,
      "step": 831
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.569667437087702e-05,
      "loss": 0.6031,
      "step": 832
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.547775395579106e-05,
      "loss": 0.6316,
      "step": 833
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.5259204751214743e-05,
      "loss": 0.6144,
      "step": 834
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.50410282451236e-05,
      "loss": 0.5955,
      "step": 835
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.48232259229554e-05,
      "loss": 0.6458,
      "step": 836
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.460579926760059e-05,
      "loss": 0.5851,
      "step": 837
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.4388749759391754e-05,
      "loss": 0.6519,
      "step": 838
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.417207887609372e-05,
      "loss": 0.6084,
      "step": 839
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.395578809289349e-05,
      "loss": 0.597,
      "step": 840
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.373987888239024e-05,
      "loss": 0.6426,
      "step": 841
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.352435271458516e-05,
      "loss": 0.6199,
      "step": 842
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.3309211056871546e-05,
      "loss": 0.6646,
      "step": 843
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.30944553740248e-05,
      "loss": 0.635,
      "step": 844
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.288008712819243e-05,
      "loss": 0.6459,
      "step": 845
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.2666107778884065e-05,
      "loss": 0.6015,
      "step": 846
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.245251878296171e-05,
      "loss": 0.6058,
      "step": 847
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.223932159462954e-05,
      "loss": 0.6235,
      "step": 848
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.202651766542416e-05,
      "loss": 0.6016,
      "step": 849
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.181410844420474e-05,
      "loss": 0.5713,
      "step": 850
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.160209537714304e-05,
      "loss": 0.6021,
      "step": 851
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.139047990771378e-05,
      "loss": 0.5759,
      "step": 852
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.1179263476684474e-05,
      "loss": 0.6291,
      "step": 853
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.096844752210598e-05,
      "loss": 0.6645,
      "step": 854
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.075803347930245e-05,
      "loss": 0.6668,
      "step": 855
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.054802278086168e-05,
      "loss": 0.6641,
      "step": 856
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.0338416856625294e-05,
      "loss": 0.6108,
      "step": 857
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.012921713367916e-05,
      "loss": 0.6225,
      "step": 858
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.9920425036343344e-05,
      "loss": 0.6502,
      "step": 859
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.971204198616284e-05,
      "loss": 0.6251,
      "step": 860
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.9504069401897505e-05,
      "loss": 0.6155,
      "step": 861
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.929650869951278e-05,
      "loss": 0.6011,
      "step": 862
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.908936129216955e-05,
      "loss": 0.6401,
      "step": 863
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.8882628590215074e-05,
      "loss": 0.6183,
      "step": 864
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.8676312001173e-05,
      "loss": 0.6188,
      "step": 865
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.84704129297339e-05,
      "loss": 0.6353,
      "step": 866
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.826493277774572e-05,
      "loss": 0.5995,
      "step": 867
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.8059872944204324e-05,
      "loss": 0.5889,
      "step": 868
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.7855234825243644e-05,
      "loss": 0.6057,
      "step": 869
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 0.6314,
      "step": 870
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.7447229301235445e-05,
      "loss": 0.6235,
      "step": 871
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.724386467406211e-05,
      "loss": 0.6153,
      "step": 872
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.704092731719892e-05,
      "loss": 0.6046,
      "step": 873
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.6838418612329305e-05,
      "loss": 0.6376,
      "step": 874
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.663633993821816e-05,
      "loss": 0.5795,
      "step": 875
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.6434692670702545e-05,
      "loss": 0.6428,
      "step": 876
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.6233478182682345e-05,
      "loss": 0.595,
      "step": 877
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.60326978441109e-05,
      "loss": 0.5972,
      "step": 878
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.583235302198562e-05,
      "loss": 0.5958,
      "step": 879
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.563244508033887e-05,
      "loss": 0.6349,
      "step": 880
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.543297538022842e-05,
      "loss": 0.6303,
      "step": 881
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.523394527972833e-05,
      "loss": 0.6197,
      "step": 882
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.503535613391973e-05,
      "loss": 0.5931,
      "step": 883
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.4837209294881467e-05,
      "loss": 0.6165,
      "step": 884
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.463950611168111e-05,
      "loss": 0.6287,
      "step": 885
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.4442247930365426e-05,
      "loss": 0.6148,
      "step": 886
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.424543609395162e-05,
      "loss": 0.6232,
      "step": 887
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.4049071942417896e-05,
      "loss": 0.6201,
      "step": 888
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.385315681269443e-05,
      "loss": 0.5763,
      "step": 889
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.365769203865425e-05,
      "loss": 0.6028,
      "step": 890
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.346267895110429e-05,
      "loss": 0.575,
      "step": 891
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.3268118877776066e-05,
      "loss": 0.6351,
      "step": 892
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.307401314331686e-05,
      "loss": 0.5671,
      "step": 893
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.288036306928055e-05,
      "loss": 0.6167,
      "step": 894
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.268716997411886e-05,
      "loss": 0.6111,
      "step": 895
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.249443517317194e-05,
      "loss": 0.6099,
      "step": 896
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.230215997865993e-05,
      "loss": 0.6065,
      "step": 897
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.211034569967365e-05,
      "loss": 0.6371,
      "step": 898
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.191899364216581e-05,
      "loss": 0.642,
      "step": 899
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.172810510894213e-05,
      "loss": 0.62,
      "step": 900
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.153768139965253e-05,
      "loss": 0.6243,
      "step": 901
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.1347723810782134e-05,
      "loss": 0.585,
      "step": 902
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.115823363564254e-05,
      "loss": 0.6031,
      "step": 903
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.0969212164362957e-05,
      "loss": 0.5605,
      "step": 904
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.078066068388162e-05,
      "loss": 0.6039,
      "step": 905
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.059258047793661e-05,
      "loss": 0.6073,
      "step": 906
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.040497282705761e-05,
      "loss": 0.6078,
      "step": 907
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.0217839008556816e-05,
      "loss": 0.5828,
      "step": 908
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.003118029652041e-05,
      "loss": 0.6259,
      "step": 909
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.9844997961799814e-05,
      "loss": 0.5911,
      "step": 910
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.9659293272003164e-05,
      "loss": 0.6255,
      "step": 911
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.947406749148649e-05,
      "loss": 0.6226,
      "step": 912
    },
    {
      "epoch": 1.48,
      "eval_loss": 0.7657160758972168,
      "eval_runtime": 85.1455,
      "eval_samples_per_second": 4.04,
      "eval_steps_per_second": 2.02,
      "step": 912
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.6314,
      "step": 913
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.9105057699405702e-05,
      "loss": 0.6158,
      "step": 914
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.8921276200216296e-05,
      "loss": 0.5916,
      "step": 915
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.873797863503923e-05,
      "loss": 0.5898,
      "step": 916
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.8555166251841802e-05,
      "loss": 0.6513,
      "step": 917
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.8372840295288106e-05,
      "loss": 0.5722,
      "step": 918
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.8191002006730328e-05,
      "loss": 0.5934,
      "step": 919
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.800965262420043e-05,
      "loss": 0.6063,
      "step": 920
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.7828793382401685e-05,
      "loss": 0.6067,
      "step": 921
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.7648425512700393e-05,
      "loss": 0.5926,
      "step": 922
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.7468550243117165e-05,
      "loss": 0.6102,
      "step": 923
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.7289168798318997e-05,
      "loss": 0.6237,
      "step": 924
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.711028239961061e-05,
      "loss": 0.6051,
      "step": 925
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.693189226492625e-05,
      "loss": 0.6248,
      "step": 926
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.675399960882138e-05,
      "loss": 0.5956,
      "step": 927
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.657660564246449e-05,
      "loss": 0.6292,
      "step": 928
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.6399711573628704e-05,
      "loss": 0.6137,
      "step": 929
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.6223318606683645e-05,
      "loss": 0.6016,
      "step": 930
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.60474279425872e-05,
      "loss": 0.6004,
      "step": 931
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.5872040778877503e-05,
      "loss": 0.6033,
      "step": 932
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.5697158309664404e-05,
      "loss": 0.6083,
      "step": 933
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.5522781725621813e-05,
      "loss": 0.6166,
      "step": 934
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.5348912213979235e-05,
      "loss": 0.6253,
      "step": 935
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.5175550958513837e-05,
      "loss": 0.5665,
      "step": 936
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.500269913954233e-05,
      "loss": 0.578,
      "step": 937
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4830357933913063e-05,
      "loss": 0.5876,
      "step": 938
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4658528514997815e-05,
      "loss": 0.6202,
      "step": 939
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.448721205268395e-05,
      "loss": 0.6108,
      "step": 940
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4316409713366352e-05,
      "loss": 0.5813,
      "step": 941
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4146122659939686e-05,
      "loss": 0.625,
      "step": 942
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3976352051790117e-05,
      "loss": 0.5991,
      "step": 943
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3807099044787818e-05,
      "loss": 0.6467,
      "step": 944
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.363836479127881e-05,
      "loss": 0.5701,
      "step": 945
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3470150440077266e-05,
      "loss": 0.5884,
      "step": 946
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3302457136457623e-05,
      "loss": 0.59,
      "step": 947
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3135286022146785e-05,
      "loss": 0.6151,
      "step": 948
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.2968638235316466e-05,
      "loss": 0.619,
      "step": 949
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.2802514910575223e-05,
      "loss": 0.67,
      "step": 950
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.2636917178960938e-05,
      "loss": 0.6182,
      "step": 951
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.2471846167932975e-05,
      "loss": 0.6125,
      "step": 952
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.230730300136461e-05,
      "loss": 0.6142,
      "step": 953
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.214328879953528e-05,
      "loss": 0.6349,
      "step": 954
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.1979804679123106e-05,
      "loss": 0.6126,
      "step": 955
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.181685175319702e-05,
      "loss": 0.5701,
      "step": 956
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.1654431131209553e-05,
      "loss": 0.6045,
      "step": 957
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.1492543918988907e-05,
      "loss": 0.6021,
      "step": 958
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.1331191218731783e-05,
      "loss": 0.6479,
      "step": 959
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.1170374128995507e-05,
      "loss": 0.6059,
      "step": 960
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.1010093744690908e-05,
      "loss": 0.5798,
      "step": 961
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0850351157074598e-05,
      "loss": 0.603,
      "step": 962
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0691147453741687e-05,
      "loss": 0.598,
      "step": 963
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0532483718618267e-05,
      "loss": 0.6349,
      "step": 964
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.037436103195426e-05,
      "loss": 0.5964,
      "step": 965
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0216780470315655e-05,
      "loss": 0.5962,
      "step": 966
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0059743106577654e-05,
      "loss": 0.5926,
      "step": 967
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9903250009916997e-05,
      "loss": 0.5832,
      "step": 968
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9747302245804945e-05,
      "loss": 0.6302,
      "step": 969
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9591900875999703e-05,
      "loss": 0.5773,
      "step": 970
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.943704695853963e-05,
      "loss": 0.6669,
      "step": 971
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9282741547735637e-05,
      "loss": 0.5901,
      "step": 972
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9128985694164237e-05,
      "loss": 0.6287,
      "step": 973
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.8975780444660273e-05,
      "loss": 0.6164,
      "step": 974
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.8823126842309956e-05,
      "loss": 0.6281,
      "step": 975
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.8671025926443465e-05,
      "loss": 0.6406,
      "step": 976
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.8519478732628247e-05,
      "loss": 0.622,
      "step": 977
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.8368486292661657e-05,
      "loss": 0.6028,
      "step": 978
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.8218049634564082e-05,
      "loss": 0.5973,
      "step": 979
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.806816978257192e-05,
      "loss": 0.5848,
      "step": 980
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.7918847757130575e-05,
      "loss": 0.5982,
      "step": 981
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.7770084574887567e-05,
      "loss": 0.6131,
      "step": 982
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.762188124868557e-05,
      "loss": 0.6049,
      "step": 983
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.7474238787555476e-05,
      "loss": 0.5957,
      "step": 984
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.7327158196709613e-05,
      "loss": 0.6309,
      "step": 985
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.7180640477534847e-05,
      "loss": 0.5919,
      "step": 986
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.7034686627585762e-05,
      "loss": 0.6028,
      "step": 987
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.6889297640577915e-05,
      "loss": 0.6332,
      "step": 988
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.6744474506381023e-05,
      "loss": 0.6137,
      "step": 989
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.660021821101222e-05,
      "loss": 0.5919,
      "step": 990
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.6456529736629345e-05,
      "loss": 0.6188,
      "step": 991
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.6313410061524393e-05,
      "loss": 0.6103,
      "step": 992
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.617086016011652e-05,
      "loss": 0.6072,
      "step": 993
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.6028881002945818e-05,
      "loss": 0.6028,
      "step": 994
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.588747355666642e-05,
      "loss": 0.6142,
      "step": 995
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.5746638784040025e-05,
      "loss": 0.611,
      "step": 996
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.5606377643929304e-05,
      "loss": 0.5899,
      "step": 997
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.5466691091291454e-05,
      "loss": 0.5974,
      "step": 998
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.5327580077171587e-05,
      "loss": 0.6,
      "step": 999
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.5189045548696323e-05,
      "loss": 0.6027,
      "step": 1000
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.5051088449067285e-05,
      "loss": 0.5911,
      "step": 1001
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.4913709717554836e-05,
      "loss": 0.6362,
      "step": 1002
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.4776910289491385e-05,
      "loss": 0.6421,
      "step": 1003
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.4640691096265358e-05,
      "loss": 0.5892,
      "step": 1004
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.4505053065314611e-05,
      "loss": 0.6197,
      "step": 1005
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.4369997120120227e-05,
      "loss": 0.6109,
      "step": 1006
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.4235524180200166e-05,
      "loss": 0.6174,
      "step": 1007
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.4101635161103132e-05,
      "loss": 0.5992,
      "step": 1008
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.3968330974402166e-05,
      "loss": 0.5969,
      "step": 1009
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3835612527688536e-05,
      "loss": 0.5847,
      "step": 1010
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3703480724565577e-05,
      "loss": 0.5945,
      "step": 1011
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3571936464642466e-05,
      "loss": 0.6101,
      "step": 1012
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3440980643528144e-05,
      "loss": 0.5834,
      "step": 1013
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3310614152825273e-05,
      "loss": 0.5992,
      "step": 1014
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3180837880124041e-05,
      "loss": 0.5864,
      "step": 1015
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.3051652708996177e-05,
      "loss": 0.6135,
      "step": 1016
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.2923059518988979e-05,
      "loss": 0.5895,
      "step": 1017
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.2795059185619229e-05,
      "loss": 0.5777,
      "step": 1018
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.2667652580367417e-05,
      "loss": 0.6203,
      "step": 1019
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.2540840570671497e-05,
      "loss": 0.6326,
      "step": 1020
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.241462401992134e-05,
      "loss": 0.6522,
      "step": 1021
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.2289003787452557e-05,
      "loss": 0.6259,
      "step": 1022
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.2163980728540835e-05,
      "loss": 0.5912,
      "step": 1023
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.203955569439601e-05,
      "loss": 0.6232,
      "step": 1024
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.1915729532156372e-05,
      "loss": 0.5949,
      "step": 1025
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.1792503084882789e-05,
      "loss": 0.6771,
      "step": 1026
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.1669877191553035e-05,
      "loss": 0.6159,
      "step": 1027
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.1547852687056015e-05,
      "loss": 0.6145,
      "step": 1028
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.142643040218624e-05,
      "loss": 0.5854,
      "step": 1029
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.1305611163637886e-05,
      "loss": 0.6001,
      "step": 1030
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.1185395793999497e-05,
      "loss": 0.6265,
      "step": 1031
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.1065785111748117e-05,
      "loss": 0.5825,
      "step": 1032
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.0946779931243866e-05,
      "loss": 0.6245,
      "step": 1033
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0828381062724324e-05,
      "loss": 0.6088,
      "step": 1034
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0710589312299091e-05,
      "loss": 0.6472,
      "step": 1035
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0593405481944208e-05,
      "loss": 0.5932,
      "step": 1036
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0476830369496759e-05,
      "loss": 0.6457,
      "step": 1037
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0360864768649381e-05,
      "loss": 0.6007,
      "step": 1038
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.0245509468944992e-05,
      "loss": 0.5875,
      "step": 1039
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.0130765255771169e-05,
      "loss": 0.6033,
      "step": 1040
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.0016632910355117e-05,
      "loss": 0.6187,
      "step": 1041
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.903113209758096e-06,
      "loss": 0.6186,
      "step": 1042
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.790206926870215e-06,
      "loss": 0.605,
      "step": 1043
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.67791483040521e-06,
      "loss": 0.6126,
      "step": 1044
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.566237684895174e-06,
      "loss": 0.5884,
      "step": 1045
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.455176250685338e-06,
      "loss": 0.6369,
      "step": 1046
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.34473128392892e-06,
      "loss": 0.5897,
      "step": 1047
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.234903536581952e-06,
      "loss": 0.6064,
      "step": 1048
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.125693756398202e-06,
      "loss": 0.5812,
      "step": 1049
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.017102686924028e-06,
      "loss": 0.5841,
      "step": 1050
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.909131067493348e-06,
      "loss": 0.6302,
      "step": 1051
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.80177963322263e-06,
      "loss": 0.6364,
      "step": 1052
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.695049115005837e-06,
      "loss": 0.6014,
      "step": 1053
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.58894023950948e-06,
      "loss": 0.63,
      "step": 1054
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.483453729167622e-06,
      "loss": 0.5974,
      "step": 1055
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.378590302177102e-06,
      "loss": 0.5789,
      "step": 1056
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.274350672492415e-06,
      "loss": 0.5855,
      "step": 1057
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.170735549821085e-06,
      "loss": 0.5755,
      "step": 1058
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.067745639618684e-06,
      "loss": 0.6208,
      "step": 1059
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.96538164308407e-06,
      "loss": 0.6193,
      "step": 1060
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.8636442571546e-06,
      "loss": 0.6176,
      "step": 1061
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.76253417450149e-06,
      "loss": 0.6062,
      "step": 1062
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.662052083524863e-06,
      "loss": 0.598,
      "step": 1063
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.562198668349352e-06,
      "loss": 0.6179,
      "step": 1064
    },
    {
      "epoch": 1.73,
      "eval_loss": 0.7634007930755615,
      "eval_runtime": 85.1365,
      "eval_samples_per_second": 4.041,
      "eval_steps_per_second": 2.02,
      "step": 1064
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.462974608819196e-06,
      "loss": 0.5789,
      "step": 1065
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.364380580493813e-06,
      "loss": 0.5975,
      "step": 1066
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.2664172546429655e-06,
      "loss": 0.5997,
      "step": 1067
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.169085298242473e-06,
      "loss": 0.5961,
      "step": 1068
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.0723853739694364e-06,
      "loss": 0.6169,
      "step": 1069
    },
    {
      "epoch": 1.74,
      "learning_rate": 6.976318140197835e-06,
      "loss": 0.6022,
      "step": 1070
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.8808842509940015e-06,
      "loss": 0.6031,
      "step": 1071
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.7860843561122765e-06,
      "loss": 0.6349,
      "step": 1072
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.6919191009903734e-06,
      "loss": 0.6348,
      "step": 1073
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.598389126745208e-06,
      "loss": 0.5898,
      "step": 1074
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.505495070168388e-06,
      "loss": 0.6201,
      "step": 1075
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.413237563721941e-06,
      "loss": 0.5842,
      "step": 1076
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.321617235533983e-06,
      "loss": 0.5944,
      "step": 1077
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.230634709394478e-06,
      "loss": 0.6038,
      "step": 1078
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.14029060475092e-06,
      "loss": 0.579,
      "step": 1079
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.0505855367041895e-06,
      "loss": 0.6069,
      "step": 1080
    },
    {
      "epoch": 1.76,
      "learning_rate": 5.961520116004327e-06,
      "loss": 0.5673,
      "step": 1081
    },
    {
      "epoch": 1.76,
      "learning_rate": 5.873094949046387e-06,
      "loss": 0.6219,
      "step": 1082
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.785310637866304e-06,
      "loss": 0.6108,
      "step": 1083
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.698167780136765e-06,
      "loss": 0.584,
      "step": 1084
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.611666969163243e-06,
      "loss": 0.5838,
      "step": 1085
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.525808793879838e-06,
      "loss": 0.6369,
      "step": 1086
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.440593838845287e-06,
      "loss": 0.5986,
      "step": 1087
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.3560226842390596e-06,
      "loss": 0.5642,
      "step": 1088
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.2720959058573775e-06,
      "loss": 0.5715,
      "step": 1089
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.188814075109172e-06,
      "loss": 0.6014,
      "step": 1090
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.106177759012421e-06,
      "loss": 0.5684,
      "step": 1091
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.024187520190104e-06,
      "loss": 0.5946,
      "step": 1092
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.942843916866435e-06,
      "loss": 0.5846,
      "step": 1093
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.862147502863057e-06,
      "loss": 0.5737,
      "step": 1094
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.7820988275953045e-06,
      "loss": 0.612,
      "step": 1095
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.7026984360684205e-06,
      "loss": 0.6021,
      "step": 1096
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.623946868873819e-06,
      "loss": 0.6028,
      "step": 1097
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.5458446621854945e-06,
      "loss": 0.6202,
      "step": 1098
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.468392347756312e-06,
      "loss": 0.5804,
      "step": 1099
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.391590452914352e-06,
      "loss": 0.5767,
      "step": 1100
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.315439500559426e-06,
      "loss": 0.5897,
      "step": 1101
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.2399400091594154e-06,
      "loss": 0.5644,
      "step": 1102
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.16509249274678e-06,
      "loss": 0.5906,
      "step": 1103
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.090897460915055e-06,
      "loss": 0.5833,
      "step": 1104
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.017355418815427e-06,
      "loss": 0.6124,
      "step": 1105
    },
    {
      "epoch": 1.8,
      "learning_rate": 3.944466867153218e-06,
      "loss": 0.5998,
      "step": 1106
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.872232302184487e-06,
      "loss": 0.5699,
      "step": 1107
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.8006522157127078e-06,
      "loss": 0.6433,
      "step": 1108
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.729727095085422e-06,
      "loss": 0.6559,
      "step": 1109
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.659457423190782e-06,
      "loss": 0.5914,
      "step": 1110
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.5898436784544854e-06,
      "loss": 0.5682,
      "step": 1111
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.5208863348363263e-06,
      "loss": 0.6197,
      "step": 1112
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.4525858618270625e-06,
      "loss": 0.5735,
      "step": 1113
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.384942724445195e-06,
      "loss": 0.5803,
      "step": 1114
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.317957383233816e-06,
      "loss": 0.6515,
      "step": 1115
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.2516302942574793e-06,
      "loss": 0.6246,
      "step": 1116
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.1859619090990222e-06,
      "loss": 0.6244,
      "step": 1117
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.120952674856614e-06,
      "loss": 0.6398,
      "step": 1118
    },
    {
      "epoch": 1.83,
      "learning_rate": 3.0566030341405925e-06,
      "loss": 0.6116,
      "step": 1119
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.9929134250705427e-06,
      "loss": 0.5905,
      "step": 1120
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.9298842812722327e-06,
      "loss": 0.6441,
      "step": 1121
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.8675160318747727e-06,
      "loss": 0.6092,
      "step": 1122
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.8058091015075394e-06,
      "loss": 0.573,
      "step": 1123
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.7447639102974434e-06,
      "loss": 0.6288,
      "step": 1124
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.6843808738659324e-06,
      "loss": 0.5766,
      "step": 1125
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.6246604033262954e-06,
      "loss": 0.5889,
      "step": 1126
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.565602905280717e-06,
      "loss": 0.6127,
      "step": 1127
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.5072087818176382e-06,
      "loss": 0.5978,
      "step": 1128
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.4494784305089557e-06,
      "loss": 0.5964,
      "step": 1129
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.392412244407294e-06,
      "loss": 0.6485,
      "step": 1130
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.336010612043382e-06,
      "loss": 0.6037,
      "step": 1131
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.2802739174234146e-06,
      "loss": 0.5995,
      "step": 1132
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.225202540026361e-06,
      "loss": 0.641,
      "step": 1133
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.170796854801449e-06,
      "loss": 0.5961,
      "step": 1134
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.1170572321655868e-06,
      "loss": 0.5736,
      "step": 1135
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.063984038000888e-06,
      "loss": 0.6131,
      "step": 1136
    },
    {
      "epoch": 1.86,
      "learning_rate": 2.011577633652062e-06,
      "loss": 0.6147,
      "step": 1137
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.9598383759240946e-06,
      "loss": 0.5958,
      "step": 1138
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.9087666170797267e-06,
      "loss": 0.5917,
      "step": 1139
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.8583627048371022e-06,
      "loss": 0.603,
      "step": 1140
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.8086269823673563e-06,
      "loss": 0.5868,
      "step": 1141
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.7595597882923309e-06,
      "loss": 0.5828,
      "step": 1142
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.711161456682242e-06,
      "loss": 0.578,
      "step": 1143
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.6634323170533928e-06,
      "loss": 0.5602,
      "step": 1144
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.6163726943659419e-06,
      "loss": 0.6,
      "step": 1145
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.5699829090217278e-06,
      "loss": 0.5739,
      "step": 1146
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.5242632768619925e-06,
      "loss": 0.546,
      "step": 1147
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.4792141091653612e-06,
      "loss": 0.642,
      "step": 1148
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.4348357126456102e-06,
      "loss": 0.6245,
      "step": 1149
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.3911283894496253e-06,
      "loss": 0.6058,
      "step": 1150
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.348092437155346e-06,
      "loss": 0.5909,
      "step": 1151
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.305728148769736e-06,
      "loss": 0.5703,
      "step": 1152
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.2640358127268049e-06,
      "loss": 0.5988,
      "step": 1153
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.223015712885589e-06,
      "loss": 0.5982,
      "step": 1154
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.182668128528286e-06,
      "loss": 0.5988,
      "step": 1155
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.142993334358311e-06,
      "loss": 0.5832,
      "step": 1156
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.1039916004984441e-06,
      "loss": 0.6079,
      "step": 1157
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.0656631924889749e-06,
      "loss": 0.6358,
      "step": 1158
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.028008371285938e-06,
      "loss": 0.6094,
      "step": 1159
    },
    {
      "epoch": 1.89,
      "learning_rate": 9.910273932592584e-07,
      "loss": 0.6308,
      "step": 1160
    },
    {
      "epoch": 1.89,
      "learning_rate": 9.54720510191076e-07,
      "loss": 0.6171,
      "step": 1161
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.190879692740128e-07,
      "loss": 0.6181,
      "step": 1162
    },
    {
      "epoch": 1.9,
      "learning_rate": 8.841300131094854e-07,
      "loss": 0.6101,
      "step": 1163
    },
    {
      "epoch": 1.9,
      "learning_rate": 8.498468797060289e-07,
      "loss": 0.6303,
      "step": 1164
    },
    {
      "epoch": 1.9,
      "learning_rate": 8.162388024777201e-07,
      "loss": 0.624,
      "step": 1165
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.833060102425682e-07,
      "loss": 0.5688,
      "step": 1166
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.510487272209377e-07,
      "loss": 0.6067,
      "step": 1167
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.194671730340608e-07,
      "loss": 0.6028,
      "step": 1168
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.885615627025166e-07,
      "loss": 0.6271,
      "step": 1169
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.583321066447656e-07,
      "loss": 0.601,
      "step": 1170
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.287790106757396e-07,
      "loss": 0.6035,
      "step": 1171
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.999024760054095e-07,
      "loss": 0.609,
      "step": 1172
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.717026992374308e-07,
      "loss": 0.593,
      "step": 1173
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.441798723678115e-07,
      "loss": 0.5702,
      "step": 1174
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.173341827836021e-07,
      "loss": 0.5928,
      "step": 1175
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.91165813261607e-07,
      "loss": 0.5579,
      "step": 1176
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.6567494196715354e-07,
      "loss": 0.6063,
      "step": 1177
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.4086174245288047e-07,
      "loss": 0.6316,
      "step": 1178
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.167263836575286e-07,
      "loss": 0.5984,
      "step": 1179
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.9326902990484136e-07,
      "loss": 0.5962,
      "step": 1180
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.7048984090239934e-07,
      "loss": 0.5947,
      "step": 1181
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.4838897174055417e-07,
      "loss": 0.5751,
      "step": 1182
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.26966572891374e-07,
      "loss": 0.5789,
      "step": 1183
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.062227902076109e-07,
      "loss": 0.5617,
      "step": 1184
    },
    {
      "epoch": 1.93,
      "learning_rate": 2.8615776492170176e-07,
      "loss": 0.5793,
      "step": 1185
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.667716336448356e-07,
      "loss": 0.5986,
      "step": 1186
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.480645283659766e-07,
      "loss": 0.6085,
      "step": 1187
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.300365764510315e-07,
      "loss": 0.6116,
      "step": 1188
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.126879006419058e-07,
      "loss": 0.5837,
      "step": 1189
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.9601861905572672e-07,
      "loss": 0.6128,
      "step": 1190
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.8002884518401041e-07,
      "loss": 0.6234,
      "step": 1191
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.6471868789189603e-07,
      "loss": 0.6159,
      "step": 1192
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.50088251417424e-07,
      "loss": 0.615,
      "step": 1193
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.3613763537078105e-07,
      "loss": 0.6398,
      "step": 1194
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.228669347336564e-07,
      "loss": 0.6369,
      "step": 1195
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.102762398586088e-07,
      "loss": 0.5772,
      "step": 1196
    },
    {
      "epoch": 1.95,
      "learning_rate": 9.836563646840047e-08,
      "loss": 0.6129,
      "step": 1197
    },
    {
      "epoch": 1.96,
      "learning_rate": 8.713520565546419e-08,
      "loss": 0.5951,
      "step": 1198
    },
    {
      "epoch": 1.96,
      "learning_rate": 7.658502388131483e-08,
      "loss": 0.6081,
      "step": 1199
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.671516297606095e-08,
      "loss": 0.6155,
      "step": 1200
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.752569013788289e-08,
      "loss": 0.5952,
      "step": 1201
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.901666793261095e-08,
      "loss": 0.6325,
      "step": 1202
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.118815429324796e-08,
      "loss": 0.6421,
      "step": 1203
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.404020251963624e-08,
      "loss": 0.6316,
      "step": 1204
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.7572861278046814e-08,
      "loss": 0.6085,
      "step": 1205
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.1786174600879617e-08,
      "loss": 0.6228,
      "step": 1206
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.6680181886352676e-08,
      "loss": 0.5801,
      "step": 1207
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.2254917898213425e-08,
      "loss": 0.5944,
      "step": 1208
    },
    {
      "epoch": 1.97,
      "learning_rate": 8.510412765538877e-09,
      "loss": 0.6082,
      "step": 1209
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.44669198249137e-09,
      "loss": 0.6147,
      "step": 1210
    },
    {
      "epoch": 1.98,
      "learning_rate": 3.0637764081853372e-09,
      "loss": 0.6291,
      "step": 1211
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.3616822665096785e-09,
      "loss": 0.5948,
      "step": 1212
    },
    {
      "epoch": 1.98,
      "learning_rate": 3.4042114606114284e-10,
      "loss": 0.5951,
      "step": 1213
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0,
      "loss": 0.6044,
      "step": 1214
    }
  ],
  "logging_steps": 1,
  "max_steps": 1214,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 607,
  "total_flos": 7.967638144470221e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}