{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.912,
  "eval_steps": 156,
  "global_step": 1092,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 1.4295,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.3455,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019982190560997328,
      "loss": 1.2167,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019964381121994658,
      "loss": 1.306,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019946571682991985,
      "loss": 1.1137,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019928762243989317,
      "loss": 0.9356,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019910952804986644,
      "loss": 0.8762,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019893143365983974,
      "loss": 1.2792,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000198753339269813,
      "loss": 0.9902,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001985752448797863,
      "loss": 0.9053,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019839715048975957,
      "loss": 1.042,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019821905609973287,
      "loss": 1.0665,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019804096170970617,
      "loss": 0.9533,
      "step": 13
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019786286731967944,
      "loss": 0.8653,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019768477292965274,
      "loss": 0.749,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000197506678539626,
      "loss": 0.8665,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001973285841495993,
      "loss": 0.3864,
      "step": 17
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019715048975957257,
      "loss": 0.9109,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019697239536954587,
      "loss": 1.0354,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019679430097951917,
      "loss": 1.1834,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019661620658949244,
      "loss": 0.8403,
      "step": 21
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019643811219946573,
      "loss": 1.0325,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000196260017809439,
      "loss": 0.9493,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001960819234194123,
      "loss": 0.9995,
      "step": 24
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019590382902938557,
      "loss": 1.0611,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019572573463935887,
      "loss": 0.8022,
      "step": 26
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019554764024933216,
      "loss": 0.3385,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019536954585930543,
      "loss": 0.9965,
      "step": 28
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019519145146927873,
      "loss": 0.9474,
      "step": 29
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000195013357079252,
      "loss": 0.9355,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001948352626892253,
      "loss": 0.786,
      "step": 31
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019465716829919857,
      "loss": 0.9528,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019447907390917187,
      "loss": 0.5179,
      "step": 33
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019430097951914516,
      "loss": 1.0531,
      "step": 34
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019412288512911846,
      "loss": 1.0949,
      "step": 35
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019394479073909173,
      "loss": 1.0082,
      "step": 36
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000193766696349065,
      "loss": 0.5266,
      "step": 37
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001935886019590383,
      "loss": 0.9854,
      "step": 38
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019341050756901157,
      "loss": 0.7773,
      "step": 39
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019323241317898486,
      "loss": 0.675,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019305431878895816,
      "loss": 0.78,
      "step": 41
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019287622439893146,
      "loss": 0.8928,
      "step": 42
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019269813000890473,
      "loss": 0.8557,
      "step": 43
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019252003561887803,
      "loss": 1.1408,
      "step": 44
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001923419412288513,
      "loss": 0.3607,
      "step": 45
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001921638468388246,
      "loss": 0.4096,
      "step": 46
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019198575244879786,
      "loss": 0.8893,
      "step": 47
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019180765805877116,
      "loss": 0.7385,
      "step": 48
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019162956366874446,
      "loss": 0.7721,
      "step": 49
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019145146927871773,
      "loss": 0.8139,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019127337488869102,
      "loss": 0.8297,
      "step": 51
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001910952804986643,
      "loss": 0.5069,
      "step": 52
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001909171861086376,
      "loss": 0.8205,
      "step": 53
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019073909171861086,
      "loss": 0.8154,
      "step": 54
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019056099732858416,
      "loss": 0.7765,
      "step": 55
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019038290293855745,
      "loss": 0.9416,
      "step": 56
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019020480854853072,
      "loss": 0.3363,
      "step": 57
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019002671415850402,
      "loss": 0.4339,
      "step": 58
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001898486197684773,
      "loss": 0.8589,
      "step": 59
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001896705253784506,
      "loss": 1.0326,
      "step": 60
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018949243098842386,
      "loss": 0.8329,
      "step": 61
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018931433659839716,
      "loss": 0.7575,
      "step": 62
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018913624220837045,
      "loss": 0.4671,
      "step": 63
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018895814781834372,
      "loss": 0.8195,
      "step": 64
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018878005342831702,
      "loss": 0.7257,
      "step": 65
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001886019590382903,
      "loss": 0.7636,
      "step": 66
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018842386464826359,
      "loss": 0.8273,
      "step": 67
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018824577025823686,
      "loss": 0.7633,
      "step": 68
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018806767586821018,
      "loss": 0.8532,
      "step": 69
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018788958147818345,
      "loss": 0.7717,
      "step": 70
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018771148708815675,
      "loss": 0.8852,
      "step": 71
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018753339269813002,
      "loss": 0.3202,
      "step": 72
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001873552983081033,
      "loss": 0.6955,
      "step": 73
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018717720391807658,
      "loss": 0.8806,
      "step": 74
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018699910952804985,
      "loss": 0.3793,
      "step": 75
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018682101513802318,
      "loss": 0.7618,
      "step": 76
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018664292074799645,
      "loss": 0.8192,
      "step": 77
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018646482635796975,
      "loss": 0.4192,
      "step": 78
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018628673196794302,
      "loss": 0.8385,
      "step": 79
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001861086375779163,
      "loss": 0.4327,
      "step": 80
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018593054318788958,
      "loss": 0.8979,
      "step": 81
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018575244879786285,
      "loss": 0.9529,
      "step": 82
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018557435440783618,
      "loss": 0.8436,
      "step": 83
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018539626001780945,
      "loss": 0.6772,
      "step": 84
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018521816562778274,
      "loss": 0.7147,
      "step": 85
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018504007123775601,
      "loss": 0.767,
      "step": 86
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001848619768477293,
      "loss": 0.8866,
      "step": 87
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018468388245770258,
      "loss": 0.8675,
      "step": 88
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018450578806767588,
      "loss": 0.7725,
      "step": 89
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018432769367764917,
      "loss": 0.9603,
      "step": 90
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018414959928762244,
      "loss": 0.7294,
      "step": 91
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018397150489759574,
      "loss": 0.7915,
      "step": 92
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000183793410507569,
      "loss": 0.8872,
      "step": 93
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001836153161175423,
      "loss": 0.8274,
      "step": 94
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018343722172751558,
      "loss": 0.8482,
      "step": 95
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018325912733748888,
      "loss": 0.7448,
      "step": 96
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018308103294746217,
      "loss": 0.7057,
      "step": 97
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018290293855743544,
      "loss": 0.9329,
      "step": 98
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018272484416740874,
      "loss": 0.8465,
      "step": 99
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000182546749777382,
      "loss": 0.391,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001823686553873553,
      "loss": 0.0,
      "step": 101
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018219056099732858,
      "loss": 0.8871,
      "step": 102
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018201246660730187,
      "loss": 0.7289,
      "step": 103
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018183437221727517,
      "loss": 0.5009,
      "step": 104
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018165627782724847,
      "loss": 0.6576,
      "step": 105
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018147818343722174,
      "loss": 0.7306,
      "step": 106
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000181300089047195,
      "loss": 0.3679,
      "step": 107
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001811219946571683,
      "loss": 0.7107,
      "step": 108
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00018094390026714157,
      "loss": 0.3577,
      "step": 109
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00018076580587711487,
      "loss": 0.8751,
      "step": 110
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018058771148708817,
      "loss": 0.9237,
      "step": 111
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018040961709706147,
      "loss": 0.8281,
      "step": 112
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018023152270703474,
      "loss": 0.3885,
      "step": 113
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018005342831700803,
      "loss": 0.826,
      "step": 114
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001798753339269813,
      "loss": 0.7249,
      "step": 115
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001796972395369546,
      "loss": 0.7137,
      "step": 116
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017951914514692787,
      "loss": 0.4369,
      "step": 117
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017934105075690117,
      "loss": 0.4071,
      "step": 118
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017916295636687446,
      "loss": 0.9597,
      "step": 119
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017898486197684773,
      "loss": 0.838,
      "step": 120
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017880676758682103,
      "loss": 0.8103,
      "step": 121
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001786286731967943,
      "loss": 0.7322,
      "step": 122
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001784505788067676,
      "loss": 1.0234,
      "step": 123
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017827248441674087,
      "loss": 0.8578,
      "step": 124
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017809439002671417,
      "loss": 1.0393,
      "step": 125
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017791629563668746,
      "loss": 0.8359,
      "step": 126
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017773820124666073,
      "loss": 0.7979,
      "step": 127
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017756010685663403,
      "loss": 0.7395,
      "step": 128
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001773820124666073,
      "loss": 0.6665,
      "step": 129
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001772039180765806,
      "loss": 0.8745,
      "step": 130
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00017702582368655387,
      "loss": 0.7065,
      "step": 131
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00017684772929652716,
      "loss": 0.3072,
      "step": 132
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00017666963490650046,
      "loss": 0.718,
      "step": 133
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00017649154051647373,
      "loss": 0.8404,
      "step": 134
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00017631344612644703,
      "loss": 0.7236,
      "step": 135
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001761353517364203,
      "loss": 0.6529,
      "step": 136
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001759572573463936,
      "loss": 0.4177,
      "step": 137
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00017577916295636686,
      "loss": 0.7227,
      "step": 138
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001756010685663402,
      "loss": 0.8079,
      "step": 139
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00017542297417631346,
      "loss": 0.4759,
      "step": 140
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00017524487978628676,
      "loss": 0.6804,
      "step": 141
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00017506678539626003,
      "loss": 0.773,
      "step": 142
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001748886910062333,
      "loss": 0.847,
      "step": 143
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001747105966162066,
      "loss": 0.8355,
      "step": 144
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001745325022261799,
      "loss": 0.8926,
      "step": 145
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001743544078361532,
      "loss": 0.672,
      "step": 146
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00017417631344612646,
      "loss": 0.3974,
      "step": 147
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00017399821905609975,
      "loss": 0.6902,
      "step": 148
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00017382012466607302,
      "loss": 0.7488,
      "step": 149
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00017364203027604632,
      "loss": 0.6907,
      "step": 150
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001734639358860196,
      "loss": 0.6857,
      "step": 151
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001732858414959929,
      "loss": 0.7513,
      "step": 152
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017310774710596618,
      "loss": 0.7948,
      "step": 153
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017292965271593945,
      "loss": 0.8763,
      "step": 154
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017275155832591275,
      "loss": 0.9951,
      "step": 155
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017257346393588602,
      "loss": 0.7795,
      "step": 156
    },
    {
      "epoch": 0.42,
      "eval_loss": 0.7492814064025879,
      "eval_runtime": 3075.3295,
      "eval_samples_per_second": 0.976,
      "eval_steps_per_second": 0.061,
      "step": 156
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017239536954585932,
      "loss": 0.7795,
      "step": 157
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001722172751558326,
      "loss": 0.75,
      "step": 158
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017203918076580589,
      "loss": 0.7877,
      "step": 159
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017186108637577918,
      "loss": 0.9346,
      "step": 160
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017168299198575245,
      "loss": 0.7944,
      "step": 161
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017150489759572575,
      "loss": 0.7398,
      "step": 162
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017132680320569902,
      "loss": 0.8405,
      "step": 163
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017114870881567232,
      "loss": 0.7651,
      "step": 164
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001709706144256456,
      "loss": 0.7257,
      "step": 165
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017079252003561888,
      "loss": 0.7083,
      "step": 166
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017061442564559218,
      "loss": 0.7598,
      "step": 167
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017043633125556545,
      "loss": 0.7595,
      "step": 168
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017025823686553875,
      "loss": 0.0,
      "step": 169
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017008014247551202,
      "loss": 0.8517,
      "step": 170
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00016990204808548531,
      "loss": 0.6331,
      "step": 171
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00016972395369545858,
      "loss": 0.7086,
      "step": 172
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001695458593054319,
      "loss": 0.3294,
      "step": 173
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00016936776491540518,
      "loss": 0.6783,
      "step": 174
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00016918967052537848,
      "loss": 0.7448,
      "step": 175
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00016901157613535175,
      "loss": 0.7255,
      "step": 176
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00016883348174532502,
      "loss": 0.8362,
      "step": 177
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001686553873552983,
      "loss": 0.6382,
      "step": 178
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00016847729296527158,
      "loss": 0.8469,
      "step": 179
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001682991985752449,
      "loss": 0.7967,
      "step": 180
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00016812110418521818,
      "loss": 0.7722,
      "step": 181
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00016794300979519147,
      "loss": 0.7976,
      "step": 182
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00016776491540516474,
      "loss": 0.6826,
      "step": 183
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00016758682101513804,
      "loss": 0.8447,
      "step": 184
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001674087266251113,
      "loss": 0.652,
      "step": 185
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001672306322350846,
      "loss": 0.8129,
      "step": 186
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001670525378450579,
      "loss": 0.9252,
      "step": 187
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00016687444345503117,
      "loss": 0.411,
      "step": 188
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00016669634906500447,
      "loss": 0.789,
      "step": 189
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016651825467497774,
      "loss": 0.7202,
      "step": 190
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016634016028495104,
      "loss": 0.645,
      "step": 191
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001661620658949243,
      "loss": 0.8303,
      "step": 192
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001659839715048976,
      "loss": 0.8786,
      "step": 193
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001658058771148709,
      "loss": 0.7888,
      "step": 194
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016562778272484417,
      "loss": 0.8448,
      "step": 195
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016544968833481747,
      "loss": 0.7375,
      "step": 196
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016527159394479074,
      "loss": 0.3857,
      "step": 197
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016509349955476404,
      "loss": 0.3874,
      "step": 198
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001649154051647373,
      "loss": 0.6513,
      "step": 199
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001647373107747106,
      "loss": 0.6204,
      "step": 200
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001645592163846839,
      "loss": 0.7956,
      "step": 201
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016438112199465717,
      "loss": 0.7612,
      "step": 202
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016420302760463047,
      "loss": 0.8245,
      "step": 203
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016402493321460374,
      "loss": 0.7008,
      "step": 204
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016384683882457704,
      "loss": 0.7392,
      "step": 205
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001636687444345503,
      "loss": 0.818,
      "step": 206
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001634906500445236,
      "loss": 0.8982,
      "step": 207
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001633125556544969,
      "loss": 0.7238,
      "step": 208
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001631344612644702,
      "loss": 0.8638,
      "step": 209
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016295636687444347,
      "loss": 0.8059,
      "step": 210
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016277827248441674,
      "loss": 0.7457,
      "step": 211
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016260017809439003,
      "loss": 0.6653,
      "step": 212
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001624220837043633,
      "loss": 0.3836,
      "step": 213
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001622439893143366,
      "loss": 0.7131,
      "step": 214
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001620658949243099,
      "loss": 0.744,
      "step": 215
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001618878005342832,
      "loss": 0.6956,
      "step": 216
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016170970614425646,
      "loss": 0.881,
      "step": 217
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016153161175422976,
      "loss": 0.8571,
      "step": 218
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016135351736420303,
      "loss": 0.8178,
      "step": 219
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016117542297417633,
      "loss": 0.6912,
      "step": 220
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001609973285841496,
      "loss": 0.7055,
      "step": 221
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001608192341941229,
      "loss": 0.7527,
      "step": 222
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001606411398040962,
      "loss": 0.7784,
      "step": 223
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016046304541406946,
      "loss": 0.759,
      "step": 224
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016028495102404276,
      "loss": 0.9544,
      "step": 225
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016010685663401603,
      "loss": 0.7427,
      "step": 226
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015992876224398933,
      "loss": 0.612,
      "step": 227
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001597506678539626,
      "loss": 0.7389,
      "step": 228
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001595725734639359,
      "loss": 0.3279,
      "step": 229
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001593944790739092,
      "loss": 0.7942,
      "step": 230
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015921638468388246,
      "loss": 0.7038,
      "step": 231
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015903829029385576,
      "loss": 0.9062,
      "step": 232
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015886019590382903,
      "loss": 0.3263,
      "step": 233
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015868210151380232,
      "loss": 0.783,
      "step": 234
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001585040071237756,
      "loss": 0.7146,
      "step": 235
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001583259127337489,
      "loss": 0.7713,
      "step": 236
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001581478183437222,
      "loss": 0.8108,
      "step": 237
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015796972395369546,
      "loss": 0.8813,
      "step": 238
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015779162956366876,
      "loss": 0.8187,
      "step": 239
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015761353517364203,
      "loss": 0.8153,
      "step": 240
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015743544078361532,
      "loss": 0.7603,
      "step": 241
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001572573463935886,
      "loss": 0.7647,
      "step": 242
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015707925200356192,
      "loss": 0.0,
      "step": 243
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001569011576135352,
      "loss": 0.7422,
      "step": 244
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015672306322350848,
      "loss": 0.6771,
      "step": 245
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015654496883348175,
      "loss": 0.6732,
      "step": 246
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015636687444345502,
      "loss": 0.3087,
      "step": 247
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015618878005342832,
      "loss": 0.3659,
      "step": 248
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001560106856634016,
      "loss": 0.637,
      "step": 249
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015583259127337491,
      "loss": 0.7033,
      "step": 250
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015565449688334818,
      "loss": 0.7298,
      "step": 251
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015547640249332148,
      "loss": 0.4897,
      "step": 252
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015529830810329475,
      "loss": 0.7378,
      "step": 253
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015512021371326805,
      "loss": 0.7567,
      "step": 254
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015494211932324132,
      "loss": 0.709,
      "step": 255
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001547640249332146,
      "loss": 0.6512,
      "step": 256
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001545859305431879,
      "loss": 0.3269,
      "step": 257
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015440783615316118,
      "loss": 0.7823,
      "step": 258
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015422974176313448,
      "loss": 0.3131,
      "step": 259
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015405164737310775,
      "loss": 0.7399,
      "step": 260
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015387355298308105,
      "loss": 0.6869,
      "step": 261
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015369545859305432,
      "loss": 0.6797,
      "step": 262
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015351736420302761,
      "loss": 0.7374,
      "step": 263
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001533392698130009,
      "loss": 0.6817,
      "step": 264
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00015316117542297418,
      "loss": 0.8483,
      "step": 265
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00015298308103294748,
      "loss": 0.7078,
      "step": 266
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00015280498664292075,
      "loss": 0.7772,
      "step": 267
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00015262689225289405,
      "loss": 0.3639,
      "step": 268
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00015244879786286731,
      "loss": 0.7033,
      "step": 269
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001522707034728406,
      "loss": 0.7402,
      "step": 270
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001520926090828139,
      "loss": 0.3391,
      "step": 271
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015191451469278718,
      "loss": 0.8637,
      "step": 272
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015173642030276048,
      "loss": 0.6696,
      "step": 273
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015155832591273375,
      "loss": 0.7798,
      "step": 274
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015138023152270704,
      "loss": 0.3043,
      "step": 275
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001512021371326803,
      "loss": 0.2661,
      "step": 276
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001510240427426536,
      "loss": 0.8184,
      "step": 277
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001508459483526269,
      "loss": 0.0,
      "step": 278
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001506678539626002,
      "loss": 0.3891,
      "step": 279
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015048975957257347,
      "loss": 0.5484,
      "step": 280
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015031166518254674,
      "loss": 0.5203,
      "step": 281
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015013357079252004,
      "loss": 0.7173,
      "step": 282
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001499554764024933,
      "loss": 0.7254,
      "step": 283
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001497773820124666,
      "loss": 0.7333,
      "step": 284
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001495992876224399,
      "loss": 0.821,
      "step": 285
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001494211932324132,
      "loss": 0.8437,
      "step": 286
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00014924309884238647,
      "loss": 0.6812,
      "step": 287
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00014906500445235977,
      "loss": 0.4667,
      "step": 288
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00014888691006233304,
      "loss": 0.6531,
      "step": 289
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00014870881567230634,
      "loss": 0.7693,
      "step": 290
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001485307212822796,
      "loss": 0.6915,
      "step": 291
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001483526268922529,
      "loss": 0.3783,
      "step": 292
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001481745325022262,
      "loss": 0.6953,
      "step": 293
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00014799643811219947,
      "loss": 0.6734,
      "step": 294
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014781834372217277,
      "loss": 0.6847,
      "step": 295
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014764024933214604,
      "loss": 0.8625,
      "step": 296
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014746215494211933,
      "loss": 0.912,
      "step": 297
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001472840605520926,
      "loss": 0.3658,
      "step": 298
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001471059661620659,
      "loss": 0.6601,
      "step": 299
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001469278717720392,
      "loss": 0.3216,
      "step": 300
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00014674977738201247,
      "loss": 0.7748,
      "step": 301
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00014657168299198577,
      "loss": 0.4081,
      "step": 302
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00014639358860195904,
      "loss": 0.488,
      "step": 303
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00014621549421193233,
      "loss": 0.7204,
      "step": 304
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001460373998219056,
      "loss": 0.4449,
      "step": 305
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001458593054318789,
      "loss": 0.4268,
      "step": 306
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001456812110418522,
      "loss": 0.7598,
      "step": 307
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014550311665182547,
      "loss": 0.3935,
      "step": 308
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014532502226179876,
      "loss": 0.4371,
      "step": 309
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014514692787177203,
      "loss": 0.6249,
      "step": 310
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014496883348174533,
      "loss": 0.2442,
      "step": 311
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001447907390917186,
      "loss": 0.377,
      "step": 312
    },
    {
      "epoch": 0.83,
      "eval_loss": 0.7219565510749817,
      "eval_runtime": 3073.748,
      "eval_samples_per_second": 0.976,
      "eval_steps_per_second": 0.061,
      "step": 312
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014461264470169192,
      "loss": 0.9249,
      "step": 313
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001444345503116652,
      "loss": 0.7808,
      "step": 314
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014425645592163846,
      "loss": 0.6411,
      "step": 315
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014407836153161176,
      "loss": 0.7279,
      "step": 316
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014390026714158503,
      "loss": 0.7926,
      "step": 317
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014372217275155833,
      "loss": 0.7047,
      "step": 318
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001435440783615316,
      "loss": 1.0378,
      "step": 319
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014336598397150492,
      "loss": 0.8464,
      "step": 320
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001431878895814782,
      "loss": 0.7573,
      "step": 321
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001430097951914515,
      "loss": 0.0,
      "step": 322
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00014283170080142476,
      "loss": 0.768,
      "step": 323
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00014265360641139806,
      "loss": 0.6512,
      "step": 324
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014247551202137133,
      "loss": 0.7085,
      "step": 325
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001422974176313446,
      "loss": 0.6705,
      "step": 326
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014211932324131792,
      "loss": 0.2988,
      "step": 327
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001419412288512912,
      "loss": 0.8387,
      "step": 328
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001417631344612645,
      "loss": 0.6611,
      "step": 329
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014158504007123776,
      "loss": 0.7045,
      "step": 330
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014140694568121105,
      "loss": 0.6521,
      "step": 331
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00014122885129118432,
      "loss": 0.6822,
      "step": 332
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00014105075690115762,
      "loss": 0.7175,
      "step": 333
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00014087266251113092,
      "loss": 0.6728,
      "step": 334
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001406945681211042,
      "loss": 0.7334,
      "step": 335
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00014051647373107749,
      "loss": 0.3581,
      "step": 336
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00014033837934105076,
      "loss": 0.3499,
      "step": 337
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00014016028495102405,
      "loss": 0.2999,
      "step": 338
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00013998219056099732,
      "loss": 0.7995,
      "step": 339
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00013980409617097062,
      "loss": 0.8377,
      "step": 340
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00013962600178094392,
      "loss": 0.3259,
      "step": 341
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001394479073909172,
      "loss": 0.7226,
      "step": 342
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00013926981300089048,
      "loss": 0.8406,
      "step": 343
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013909171861086375,
      "loss": 0.7804,
      "step": 344
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013891362422083705,
      "loss": 0.7195,
      "step": 345
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013873552983081032,
      "loss": 0.7241,
      "step": 346
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013855743544078362,
      "loss": 0.8026,
      "step": 347
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013837934105075692,
      "loss": 0.7555,
      "step": 348
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001382012466607302,
      "loss": 0.0,
      "step": 349
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013802315227070348,
      "loss": 0.3378,
      "step": 350
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013784505788067675,
      "loss": 0.6628,
      "step": 351
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013766696349065005,
      "loss": 0.3602,
      "step": 352
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013748886910062332,
      "loss": 0.8476,
      "step": 353
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013731077471059662,
      "loss": 0.693,
      "step": 354
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001371326803205699,
      "loss": 0.8012,
      "step": 355
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001369545859305432,
      "loss": 0.3607,
      "step": 356
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013677649154051648,
      "loss": 0.8572,
      "step": 357
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013659839715048978,
      "loss": 0.396,
      "step": 358
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013642030276046305,
      "loss": 0.6467,
      "step": 359
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013624220837043632,
      "loss": 0.6621,
      "step": 360
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013606411398040961,
      "loss": 0.7438,
      "step": 361
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001358860195903829,
      "loss": 0.4458,
      "step": 362
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001357079252003562,
      "loss": 0.6783,
      "step": 363
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013552983081032948,
      "loss": 0.8403,
      "step": 364
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013535173642030278,
      "loss": 0.8368,
      "step": 365
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00013517364203027605,
      "loss": 0.7452,
      "step": 366
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00013499554764024934,
      "loss": 0.6407,
      "step": 367
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001348174532502226,
      "loss": 0.7468,
      "step": 368
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001346393588601959,
      "loss": 0.7002,
      "step": 369
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001344612644701692,
      "loss": 0.6534,
      "step": 370
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00013428317008014248,
      "loss": 0.7777,
      "step": 371
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00013410507569011577,
      "loss": 0.7862,
      "step": 372
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00013392698130008904,
      "loss": 0.7997,
      "step": 373
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013374888691006234,
      "loss": 0.5862,
      "step": 374
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001335707925200356,
      "loss": 0.7702,
      "step": 375
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001333926981300089,
      "loss": 0.5793,
      "step": 376
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001332146037399822,
      "loss": 0.6414,
      "step": 377
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013303650934995547,
      "loss": 0.6137,
      "step": 378
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013285841495992877,
      "loss": 0.7891,
      "step": 379
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013268032056990204,
      "loss": 0.6185,
      "step": 380
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013250222617987534,
      "loss": 0.6925,
      "step": 381
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001323241317898486,
      "loss": 0.3292,
      "step": 382
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013214603739982193,
      "loss": 0.5622,
      "step": 383
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001319679430097952,
      "loss": 0.5694,
      "step": 384
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00013178984861976847,
      "loss": 0.6785,
      "step": 385
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00013161175422974177,
      "loss": 0.6613,
      "step": 386
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00013143365983971504,
      "loss": 0.5935,
      "step": 387
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00013125556544968834,
      "loss": 0.6241,
      "step": 388
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001310774710596616,
      "loss": 0.6922,
      "step": 389
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013089937666963493,
      "loss": 0.2301,
      "step": 390
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001307212822796082,
      "loss": 0.7666,
      "step": 391
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001305431878895815,
      "loss": 0.6726,
      "step": 392
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013036509349955477,
      "loss": 0.6813,
      "step": 393
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013018699910952806,
      "loss": 0.5939,
      "step": 394
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013000890471950133,
      "loss": 0.5903,
      "step": 395
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001298308103294746,
      "loss": 0.6489,
      "step": 396
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00012965271593944793,
      "loss": 0.6586,
      "step": 397
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001294746215494212,
      "loss": 0.3495,
      "step": 398
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001292965271593945,
      "loss": 0.545,
      "step": 399
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00012911843276936777,
      "loss": 0.3648,
      "step": 400
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00012894033837934106,
      "loss": 0.6597,
      "step": 401
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00012876224398931433,
      "loss": 0.8109,
      "step": 402
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00012858414959928763,
      "loss": 0.6962,
      "step": 403
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00012840605520926093,
      "loss": 0.7175,
      "step": 404
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001282279608192342,
      "loss": 0.0,
      "step": 405
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001280498664292075,
      "loss": 0.8547,
      "step": 406
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012787177203918076,
      "loss": 0.5956,
      "step": 407
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012769367764915406,
      "loss": 0.6394,
      "step": 408
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012751558325912733,
      "loss": 0.6,
      "step": 409
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012733748886910063,
      "loss": 0.616,
      "step": 410
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00012715939447907392,
      "loss": 0.6407,
      "step": 411
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001269813000890472,
      "loss": 0.2916,
      "step": 412
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001268032056990205,
      "loss": 0.6721,
      "step": 413
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00012662511130899376,
      "loss": 0.8743,
      "step": 414
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012644701691896706,
      "loss": 0.6431,
      "step": 415
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012626892252894033,
      "loss": 0.7007,
      "step": 416
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012609082813891363,
      "loss": 0.2533,
      "step": 417
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012591273374888692,
      "loss": 0.672,
      "step": 418
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00012573463935886022,
      "loss": 0.3408,
      "step": 419
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001255565449688335,
      "loss": 0.7538,
      "step": 420
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00012537845057880676,
      "loss": 0.3449,
      "step": 421
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00012520035618878006,
      "loss": 0.7256,
      "step": 422
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00012502226179875333,
      "loss": 0.7291,
      "step": 423
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00012484416740872665,
      "loss": 0.6065,
      "step": 424
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00012466607301869992,
      "loss": 0.635,
      "step": 425
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012448797862867322,
      "loss": 0.671,
      "step": 426
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001243098842386465,
      "loss": 0.6314,
      "step": 427
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012413178984861979,
      "loss": 0.6545,
      "step": 428
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012395369545859306,
      "loss": 0.705,
      "step": 429
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012377560106856632,
      "loss": 0.3167,
      "step": 430
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012359750667853965,
      "loss": 0.3716,
      "step": 431
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012341941228851292,
      "loss": 0.3234,
      "step": 432
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012324131789848622,
      "loss": 0.5392,
      "step": 433
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012306322350845949,
      "loss": 0.5631,
      "step": 434
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012288512911843278,
      "loss": 0.6213,
      "step": 435
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012270703472840605,
      "loss": 0.6517,
      "step": 436
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00012252894033837935,
      "loss": 0.7252,
      "step": 437
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00012235084594835265,
      "loss": 0.4931,
      "step": 438
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00012217275155832592,
      "loss": 0.7323,
      "step": 439
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00012199465716829921,
      "loss": 0.3804,
      "step": 440
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001218165627782725,
      "loss": 0.6936,
      "step": 441
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00012163846838824577,
      "loss": 0.3008,
      "step": 442
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00012146037399821905,
      "loss": 0.3464,
      "step": 443
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00012128227960819233,
      "loss": 0.5404,
      "step": 444
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012110418521816565,
      "loss": 0.6135,
      "step": 445
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012092609082813893,
      "loss": 0.7313,
      "step": 446
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012074799643811221,
      "loss": 0.3075,
      "step": 447
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001205699020480855,
      "loss": 0.2808,
      "step": 448
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012039180765805878,
      "loss": 0.2695,
      "step": 449
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012021371326803206,
      "loss": 0.358,
      "step": 450
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012003561887800535,
      "loss": 0.5827,
      "step": 451
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00011985752448797864,
      "loss": 0.8548,
      "step": 452
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00011967943009795193,
      "loss": 0.53,
      "step": 453
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00011950133570792521,
      "loss": 0.3389,
      "step": 454
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001193232413178985,
      "loss": 0.7045,
      "step": 455
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00011914514692787178,
      "loss": 0.6601,
      "step": 456
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00011896705253784506,
      "loss": 0.6617,
      "step": 457
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00011878895814781834,
      "loss": 0.3759,
      "step": 458
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00011861086375779164,
      "loss": 0.6432,
      "step": 459
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011843276936776492,
      "loss": 0.5865,
      "step": 460
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011825467497773821,
      "loss": 0.6918,
      "step": 461
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011807658058771149,
      "loss": 0.3008,
      "step": 462
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011789848619768478,
      "loss": 0.565,
      "step": 463
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011772039180765806,
      "loss": 0.3316,
      "step": 464
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011754229741763134,
      "loss": 0.6376,
      "step": 465
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011736420302760465,
      "loss": 0.6327,
      "step": 466
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011718610863757792,
      "loss": 0.2644,
      "step": 467
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001170080142475512,
      "loss": 0.7361,
      "step": 468
    },
    {
      "epoch": 1.25,
      "eval_loss": 0.7121204137802124,
      "eval_runtime": 3029.8509,
      "eval_samples_per_second": 0.99,
      "eval_steps_per_second": 0.062,
      "step": 468
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011682991985752449,
      "loss": 0.5681,
      "step": 469
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011665182546749777,
      "loss": 0.5816,
      "step": 470
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011647373107747106,
      "loss": 0.6412,
      "step": 471
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011629563668744434,
      "loss": 0.6298,
      "step": 472
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011611754229741765,
      "loss": 0.6575,
      "step": 473
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011593944790739093,
      "loss": 0.652,
      "step": 474
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011576135351736422,
      "loss": 0.6355,
      "step": 475
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001155832591273375,
      "loss": 0.7028,
      "step": 476
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011540516473731077,
      "loss": 0.6536,
      "step": 477
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011522707034728406,
      "loss": 0.7111,
      "step": 478
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011504897595725734,
      "loss": 0.3475,
      "step": 479
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011487088156723065,
      "loss": 0.7486,
      "step": 480
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011469278717720393,
      "loss": 0.6859,
      "step": 481
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011451469278717722,
      "loss": 0.6173,
      "step": 482
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001143365983971505,
      "loss": 0.616,
      "step": 483
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011415850400712378,
      "loss": 0.682,
      "step": 484
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011398040961709707,
      "loss": 0.5704,
      "step": 485
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011380231522707035,
      "loss": 0.7536,
      "step": 486
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011362422083704365,
      "loss": 0.7496,
      "step": 487
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011344612644701693,
      "loss": 0.6929,
      "step": 488
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011326803205699021,
      "loss": 0.619,
      "step": 489
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001130899376669635,
      "loss": 0.6834,
      "step": 490
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011291184327693678,
      "loss": 0.6826,
      "step": 491
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011273374888691006,
      "loss": 0.6989,
      "step": 492
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011255565449688335,
      "loss": 0.3072,
      "step": 493
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011237756010685665,
      "loss": 0.6036,
      "step": 494
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011219946571682993,
      "loss": 0.3625,
      "step": 495
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011202137132680321,
      "loss": 0.6862,
      "step": 496
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001118432769367765,
      "loss": 0.7319,
      "step": 497
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011166518254674978,
      "loss": 0.6455,
      "step": 498
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011148708815672306,
      "loss": 0.6173,
      "step": 499
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011130899376669635,
      "loss": 0.575,
      "step": 500
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011113089937666966,
      "loss": 0.6085,
      "step": 501
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011095280498664293,
      "loss": 0.5568,
      "step": 502
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011077471059661621,
      "loss": 0.6058,
      "step": 503
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001105966162065895,
      "loss": 0.7362,
      "step": 504
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011041852181656278,
      "loss": 0.6131,
      "step": 505
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011024042742653606,
      "loss": 0.3333,
      "step": 506
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011006233303650934,
      "loss": 0.5854,
      "step": 507
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00010988423864648266,
      "loss": 0.6357,
      "step": 508
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00010970614425645594,
      "loss": 0.4692,
      "step": 509
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00010952804986642922,
      "loss": 0.608,
      "step": 510
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001093499554764025,
      "loss": 0.7262,
      "step": 511
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010917186108637578,
      "loss": 0.3735,
      "step": 512
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010899376669634906,
      "loss": 0.8646,
      "step": 513
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010881567230632234,
      "loss": 0.6547,
      "step": 514
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010863757791629565,
      "loss": 0.6472,
      "step": 515
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010845948352626894,
      "loss": 0.2993,
      "step": 516
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010828138913624222,
      "loss": 0.6381,
      "step": 517
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001081032947462155,
      "loss": 0.7432,
      "step": 518
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010792520035618879,
      "loss": 0.2643,
      "step": 519
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010774710596616207,
      "loss": 0.6846,
      "step": 520
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010756901157613535,
      "loss": 0.561,
      "step": 521
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010739091718610865,
      "loss": 0.6041,
      "step": 522
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010721282279608193,
      "loss": 0.3275,
      "step": 523
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010703472840605522,
      "loss": 0.322,
      "step": 524
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001068566340160285,
      "loss": 0.7932,
      "step": 525
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010667853962600179,
      "loss": 0.3419,
      "step": 526
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010650044523597507,
      "loss": 0.2482,
      "step": 527
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010632235084594835,
      "loss": 0.619,
      "step": 528
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010614425645592165,
      "loss": 0.5736,
      "step": 529
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010596616206589493,
      "loss": 0.6258,
      "step": 530
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010578806767586822,
      "loss": 0.2708,
      "step": 531
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001056099732858415,
      "loss": 0.7375,
      "step": 532
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010543187889581478,
      "loss": 0.7543,
      "step": 533
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010525378450578807,
      "loss": 0.6985,
      "step": 534
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010507569011576135,
      "loss": 0.6806,
      "step": 535
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010489759572573465,
      "loss": 0.5141,
      "step": 536
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010471950133570793,
      "loss": 0.6769,
      "step": 537
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010454140694568121,
      "loss": 0.334,
      "step": 538
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001043633125556545,
      "loss": 0.6568,
      "step": 539
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010418521816562778,
      "loss": 0.613,
      "step": 540
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010400712377560106,
      "loss": 0.6049,
      "step": 541
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010382902938557435,
      "loss": 0.3279,
      "step": 542
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010365093499554766,
      "loss": 0.6718,
      "step": 543
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010347284060552094,
      "loss": 0.6749,
      "step": 544
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010329474621549423,
      "loss": 0.6168,
      "step": 545
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010311665182546751,
      "loss": 0.5998,
      "step": 546
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010293855743544078,
      "loss": 0.5491,
      "step": 547
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010276046304541406,
      "loss": 0.5222,
      "step": 548
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010258236865538735,
      "loss": 0.5417,
      "step": 549
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010240427426536066,
      "loss": 0.7236,
      "step": 550
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010222617987533394,
      "loss": 0.7101,
      "step": 551
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010204808548530722,
      "loss": 0.6727,
      "step": 552
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010186999109528051,
      "loss": 0.7365,
      "step": 553
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010169189670525379,
      "loss": 0.2442,
      "step": 554
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010151380231522707,
      "loss": 0.7189,
      "step": 555
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010133570792520036,
      "loss": 0.3235,
      "step": 556
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010115761353517366,
      "loss": 0.6995,
      "step": 557
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010097951914514694,
      "loss": 0.2615,
      "step": 558
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010080142475512022,
      "loss": 0.5468,
      "step": 559
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001006233303650935,
      "loss": 0.5447,
      "step": 560
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010044523597506679,
      "loss": 0.6512,
      "step": 561
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010026714158504007,
      "loss": 0.5687,
      "step": 562
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010008904719501336,
      "loss": 0.5992,
      "step": 563
    },
    {
      "epoch": 1.5,
      "learning_rate": 9.991095280498664e-05,
      "loss": 0.7338,
      "step": 564
    },
    {
      "epoch": 1.51,
      "learning_rate": 9.973285841495992e-05,
      "loss": 0.6911,
      "step": 565
    },
    {
      "epoch": 1.51,
      "learning_rate": 9.955476402493322e-05,
      "loss": 0.4459,
      "step": 566
    },
    {
      "epoch": 1.51,
      "learning_rate": 9.93766696349065e-05,
      "loss": 0.7121,
      "step": 567
    },
    {
      "epoch": 1.51,
      "learning_rate": 9.919857524487979e-05,
      "loss": 0.5589,
      "step": 568
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.902048085485308e-05,
      "loss": 0.677,
      "step": 569
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.884238646482637e-05,
      "loss": 0.7049,
      "step": 570
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.866429207479965e-05,
      "loss": 0.6427,
      "step": 571
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.848619768477293e-05,
      "loss": 0.5861,
      "step": 572
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.830810329474622e-05,
      "loss": 0.5978,
      "step": 573
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.81300089047195e-05,
      "loss": 0.6745,
      "step": 574
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.795191451469279e-05,
      "loss": 0.6032,
      "step": 575
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.777382012466608e-05,
      "loss": 0.5781,
      "step": 576
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.759572573463937e-05,
      "loss": 0.7666,
      "step": 577
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.741763134461265e-05,
      "loss": 0.4642,
      "step": 578
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.723953695458593e-05,
      "loss": 0.2939,
      "step": 579
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.706144256455923e-05,
      "loss": 0.351,
      "step": 580
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.68833481745325e-05,
      "loss": 0.2853,
      "step": 581
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.670525378450578e-05,
      "loss": 0.6338,
      "step": 582
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.652715939447908e-05,
      "loss": 0.797,
      "step": 583
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.634906500445236e-05,
      "loss": 0.2846,
      "step": 584
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.617097061442565e-05,
      "loss": 0.7644,
      "step": 585
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.599287622439893e-05,
      "loss": 0.3915,
      "step": 586
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.581478183437223e-05,
      "loss": 0.6562,
      "step": 587
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.563668744434551e-05,
      "loss": 0.7001,
      "step": 588
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.54585930543188e-05,
      "loss": 0.6126,
      "step": 589
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.528049866429208e-05,
      "loss": 0.7411,
      "step": 590
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.510240427426536e-05,
      "loss": 0.7062,
      "step": 591
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.492430988423865e-05,
      "loss": 0.3634,
      "step": 592
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.474621549421193e-05,
      "loss": 0.6527,
      "step": 593
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.456812110418523e-05,
      "loss": 0.6956,
      "step": 594
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.439002671415851e-05,
      "loss": 0.5481,
      "step": 595
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.421193232413179e-05,
      "loss": 0.3675,
      "step": 596
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.403383793410509e-05,
      "loss": 0.6013,
      "step": 597
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.385574354407837e-05,
      "loss": 0.5972,
      "step": 598
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.367764915405164e-05,
      "loss": 0.6441,
      "step": 599
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.349955476402493e-05,
      "loss": 0.5255,
      "step": 600
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.332146037399822e-05,
      "loss": 0.7279,
      "step": 601
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.314336598397151e-05,
      "loss": 0.603,
      "step": 602
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.296527159394479e-05,
      "loss": 0.7985,
      "step": 603
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.278717720391809e-05,
      "loss": 0.645,
      "step": 604
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.260908281389137e-05,
      "loss": 0.4851,
      "step": 605
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.243098842386466e-05,
      "loss": 0.6799,
      "step": 606
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.225289403383794e-05,
      "loss": 0.618,
      "step": 607
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.207479964381122e-05,
      "loss": 0.7106,
      "step": 608
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.18967052537845e-05,
      "loss": 0.6385,
      "step": 609
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.171861086375779e-05,
      "loss": 0.5345,
      "step": 610
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.154051647373109e-05,
      "loss": 0.6337,
      "step": 611
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.136242208370437e-05,
      "loss": 0.2828,
      "step": 612
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.118432769367765e-05,
      "loss": 0.5525,
      "step": 613
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.100623330365094e-05,
      "loss": 0.5905,
      "step": 614
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.082813891362423e-05,
      "loss": 0.6172,
      "step": 615
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.06500445235975e-05,
      "loss": 0.2531,
      "step": 616
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.047195013357079e-05,
      "loss": 0.5794,
      "step": 617
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.029385574354408e-05,
      "loss": 0.5981,
      "step": 618
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.011576135351737e-05,
      "loss": 0.6818,
      "step": 619
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.993766696349065e-05,
      "loss": 0.4925,
      "step": 620
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.975957257346394e-05,
      "loss": 0.6088,
      "step": 621
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.958147818343723e-05,
      "loss": 0.3952,
      "step": 622
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.940338379341052e-05,
      "loss": 0.7616,
      "step": 623
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.92252894033838e-05,
      "loss": 0.2656,
      "step": 624
    },
    {
      "epoch": 1.66,
      "eval_loss": 0.703172504901886,
      "eval_runtime": 3013.5535,
      "eval_samples_per_second": 0.996,
      "eval_steps_per_second": 0.062,
      "step": 624
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.904719501335708e-05,
      "loss": 0.3456,
      "step": 625
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.886910062333037e-05,
      "loss": 0.676,
      "step": 626
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.869100623330365e-05,
      "loss": 0.5272,
      "step": 627
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.851291184327693e-05,
      "loss": 0.6658,
      "step": 628
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.833481745325023e-05,
      "loss": 0.6169,
      "step": 629
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.815672306322351e-05,
      "loss": 0.6002,
      "step": 630
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.79786286731968e-05,
      "loss": 0.7356,
      "step": 631
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.78005342831701e-05,
      "loss": 0.6897,
      "step": 632
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.762243989314338e-05,
      "loss": 0.2658,
      "step": 633
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.744434550311665e-05,
      "loss": 0.6747,
      "step": 634
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.726625111308994e-05,
      "loss": 0.6006,
      "step": 635
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.708815672306323e-05,
      "loss": 0.6688,
      "step": 636
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.691006233303651e-05,
      "loss": 0.0,
      "step": 637
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.67319679430098e-05,
      "loss": 0.6671,
      "step": 638
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.655387355298309e-05,
      "loss": 0.5724,
      "step": 639
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.637577916295638e-05,
      "loss": 0.6995,
      "step": 640
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.619768477292966e-05,
      "loss": 0.3299,
      "step": 641
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.601959038290294e-05,
      "loss": 0.6205,
      "step": 642
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.584149599287623e-05,
      "loss": 0.6103,
      "step": 643
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.566340160284951e-05,
      "loss": 0.5643,
      "step": 644
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.54853072128228e-05,
      "loss": 0.7474,
      "step": 645
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.530721282279609e-05,
      "loss": 0.0,
      "step": 646
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.512911843276937e-05,
      "loss": 0.7264,
      "step": 647
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.495102404274266e-05,
      "loss": 0.8836,
      "step": 648
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.477292965271595e-05,
      "loss": 0.7588,
      "step": 649
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.459483526268924e-05,
      "loss": 0.6704,
      "step": 650
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.441674087266251e-05,
      "loss": 0.5627,
      "step": 651
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.423864648263579e-05,
      "loss": 0.5401,
      "step": 652
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.406055209260909e-05,
      "loss": 0.8335,
      "step": 653
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.388245770258237e-05,
      "loss": 0.6584,
      "step": 654
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.370436331255566e-05,
      "loss": 0.5991,
      "step": 655
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.352626892252895e-05,
      "loss": 0.6626,
      "step": 656
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.334817453250224e-05,
      "loss": 0.5727,
      "step": 657
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.317008014247552e-05,
      "loss": 0.5497,
      "step": 658
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.29919857524488e-05,
      "loss": 0.7755,
      "step": 659
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.281389136242209e-05,
      "loss": 0.6321,
      "step": 660
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.263579697239537e-05,
      "loss": 0.6396,
      "step": 661
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.245770258236865e-05,
      "loss": 0.6499,
      "step": 662
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.227960819234195e-05,
      "loss": 0.7268,
      "step": 663
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.210151380231523e-05,
      "loss": 0.7767,
      "step": 664
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.192341941228852e-05,
      "loss": 0.5954,
      "step": 665
    },
    {
      "epoch": 1.78,
      "learning_rate": 8.17453250222618e-05,
      "loss": 0.5569,
      "step": 666
    },
    {
      "epoch": 1.78,
      "learning_rate": 8.15672306322351e-05,
      "loss": 0.4631,
      "step": 667
    },
    {
      "epoch": 1.78,
      "learning_rate": 8.138913624220837e-05,
      "loss": 0.5095,
      "step": 668
    },
    {
      "epoch": 1.78,
      "learning_rate": 8.121104185218165e-05,
      "loss": 0.5156,
      "step": 669
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.103294746215495e-05,
      "loss": 0.7886,
      "step": 670
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.085485307212823e-05,
      "loss": 0.7179,
      "step": 671
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.067675868210152e-05,
      "loss": 0.3063,
      "step": 672
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.04986642920748e-05,
      "loss": 0.6799,
      "step": 673
    },
    {
      "epoch": 1.8,
      "learning_rate": 8.03205699020481e-05,
      "loss": 0.4453,
      "step": 674
    },
    {
      "epoch": 1.8,
      "learning_rate": 8.014247551202138e-05,
      "loss": 0.6371,
      "step": 675
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.996438112199466e-05,
      "loss": 0.6388,
      "step": 676
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.978628673196795e-05,
      "loss": 0.5928,
      "step": 677
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.960819234194123e-05,
      "loss": 0.7315,
      "step": 678
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.943009795191451e-05,
      "loss": 0.3025,
      "step": 679
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.92520035618878e-05,
      "loss": 0.6875,
      "step": 680
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.90739091718611e-05,
      "loss": 0.6911,
      "step": 681
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.889581478183438e-05,
      "loss": 0.5739,
      "step": 682
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.871772039180766e-05,
      "loss": 0.5978,
      "step": 683
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.853962600178096e-05,
      "loss": 0.6027,
      "step": 684
    },
    {
      "epoch": 1.83,
      "learning_rate": 7.836153161175424e-05,
      "loss": 0.6756,
      "step": 685
    },
    {
      "epoch": 1.83,
      "learning_rate": 7.818343722172751e-05,
      "loss": 0.4417,
      "step": 686
    },
    {
      "epoch": 1.83,
      "learning_rate": 7.80053428317008e-05,
      "loss": 0.5446,
      "step": 687
    },
    {
      "epoch": 1.83,
      "learning_rate": 7.782724844167409e-05,
      "loss": 0.5871,
      "step": 688
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.764915405164738e-05,
      "loss": 0.5769,
      "step": 689
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.747105966162066e-05,
      "loss": 0.6795,
      "step": 690
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.729296527159396e-05,
      "loss": 0.7031,
      "step": 691
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.711487088156724e-05,
      "loss": 0.611,
      "step": 692
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.693677649154052e-05,
      "loss": 0.6716,
      "step": 693
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.675868210151381e-05,
      "loss": 0.5719,
      "step": 694
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.658058771148709e-05,
      "loss": 0.2431,
      "step": 695
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.640249332146037e-05,
      "loss": 0.6719,
      "step": 696
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.622439893143366e-05,
      "loss": 0.6299,
      "step": 697
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.604630454140695e-05,
      "loss": 0.7345,
      "step": 698
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.586821015138024e-05,
      "loss": 0.3209,
      "step": 699
    },
    {
      "epoch": 1.87,
      "learning_rate": 7.569011576135352e-05,
      "loss": 0.6855,
      "step": 700
    },
    {
      "epoch": 1.87,
      "learning_rate": 7.55120213713268e-05,
      "loss": 0.6889,
      "step": 701
    },
    {
      "epoch": 1.87,
      "learning_rate": 7.53339269813001e-05,
      "loss": 0.7942,
      "step": 702
    },
    {
      "epoch": 1.87,
      "learning_rate": 7.515583259127337e-05,
      "loss": 0.6145,
      "step": 703
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.497773820124666e-05,
      "loss": 0.6379,
      "step": 704
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.479964381121995e-05,
      "loss": 0.8225,
      "step": 705
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.462154942119324e-05,
      "loss": 0.7393,
      "step": 706
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.444345503116652e-05,
      "loss": 0.2515,
      "step": 707
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.42653606411398e-05,
      "loss": 0.7343,
      "step": 708
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.40872662511131e-05,
      "loss": 0.7412,
      "step": 709
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.390917186108638e-05,
      "loss": 0.631,
      "step": 710
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.373107747105967e-05,
      "loss": 0.6821,
      "step": 711
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.355298308103295e-05,
      "loss": 0.6614,
      "step": 712
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.337488869100623e-05,
      "loss": 0.7726,
      "step": 713
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.319679430097952e-05,
      "loss": 0.3381,
      "step": 714
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.30186999109528e-05,
      "loss": 0.5583,
      "step": 715
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.28406055209261e-05,
      "loss": 0.6351,
      "step": 716
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.266251113089938e-05,
      "loss": 0.639,
      "step": 717
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.248441674087267e-05,
      "loss": 0.7555,
      "step": 718
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.230632235084596e-05,
      "loss": 0.5269,
      "step": 719
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.212822796081923e-05,
      "loss": 0.6324,
      "step": 720
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.195013357079252e-05,
      "loss": 0.568,
      "step": 721
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.17720391807658e-05,
      "loss": 0.5796,
      "step": 722
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.15939447907391e-05,
      "loss": 0.6747,
      "step": 723
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.141585040071238e-05,
      "loss": 0.4163,
      "step": 724
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.123775601068566e-05,
      "loss": 0.5695,
      "step": 725
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.105966162065896e-05,
      "loss": 0.6616,
      "step": 726
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.088156723063224e-05,
      "loss": 0.3678,
      "step": 727
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.070347284060553e-05,
      "loss": 0.3138,
      "step": 728
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.052537845057881e-05,
      "loss": 0.7429,
      "step": 729
    },
    {
      "epoch": 1.95,
      "learning_rate": 7.03472840605521e-05,
      "loss": 0.7671,
      "step": 730
    },
    {
      "epoch": 1.95,
      "learning_rate": 7.016918967052538e-05,
      "loss": 0.2879,
      "step": 731
    },
    {
      "epoch": 1.95,
      "learning_rate": 6.999109528049866e-05,
      "loss": 0.6856,
      "step": 732
    },
    {
      "epoch": 1.95,
      "learning_rate": 6.981300089047196e-05,
      "loss": 0.2531,
      "step": 733
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.963490650044524e-05,
      "loss": 0.6888,
      "step": 734
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.945681211041853e-05,
      "loss": 0.3946,
      "step": 735
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.927871772039181e-05,
      "loss": 0.7019,
      "step": 736
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.91006233303651e-05,
      "loss": 0.2584,
      "step": 737
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.892252894033838e-05,
      "loss": 0.6617,
      "step": 738
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.874443455031166e-05,
      "loss": 0.2846,
      "step": 739
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.856634016028496e-05,
      "loss": 0.6521,
      "step": 740
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.838824577025824e-05,
      "loss": 0.5318,
      "step": 741
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.821015138023152e-05,
      "loss": 0.7488,
      "step": 742
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.803205699020481e-05,
      "loss": 0.6779,
      "step": 743
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.78539626001781e-05,
      "loss": 0.7625,
      "step": 744
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.767586821015139e-05,
      "loss": 0.7302,
      "step": 745
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.749777382012467e-05,
      "loss": 0.5564,
      "step": 746
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.731967943009795e-05,
      "loss": 0.5948,
      "step": 747
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.714158504007124e-05,
      "loss": 0.8588,
      "step": 748
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.696349065004452e-05,
      "loss": 0.5765,
      "step": 749
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.67853962600178e-05,
      "loss": 0.6925,
      "step": 750
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.66073018699911e-05,
      "loss": 0.4935,
      "step": 751
    },
    {
      "epoch": 2.01,
      "learning_rate": 6.642920747996439e-05,
      "loss": 0.5056,
      "step": 752
    },
    {
      "epoch": 2.01,
      "learning_rate": 6.625111308993767e-05,
      "loss": 0.5514,
      "step": 753
    },
    {
      "epoch": 2.01,
      "learning_rate": 6.607301869991097e-05,
      "loss": 0.3091,
      "step": 754
    },
    {
      "epoch": 2.01,
      "learning_rate": 6.589492430988424e-05,
      "loss": 0.6602,
      "step": 755
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.571682991985752e-05,
      "loss": 0.6998,
      "step": 756
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.55387355298308e-05,
      "loss": 0.4589,
      "step": 757
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.53606411398041e-05,
      "loss": 0.0,
      "step": 758
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.518254674977738e-05,
      "loss": 0.0,
      "step": 759
    },
    {
      "epoch": 2.03,
      "learning_rate": 6.500445235975067e-05,
      "loss": 0.523,
      "step": 760
    },
    {
      "epoch": 2.03,
      "learning_rate": 6.482635796972396e-05,
      "loss": 0.4522,
      "step": 761
    },
    {
      "epoch": 2.03,
      "learning_rate": 6.464826357969725e-05,
      "loss": 0.556,
      "step": 762
    },
    {
      "epoch": 2.03,
      "learning_rate": 6.447016918967053e-05,
      "loss": 0.5423,
      "step": 763
    },
    {
      "epoch": 2.04,
      "learning_rate": 6.429207479964381e-05,
      "loss": 0.4313,
      "step": 764
    },
    {
      "epoch": 2.04,
      "learning_rate": 6.41139804096171e-05,
      "loss": 0.6231,
      "step": 765
    },
    {
      "epoch": 2.04,
      "learning_rate": 6.393588601959038e-05,
      "loss": 0.4847,
      "step": 766
    },
    {
      "epoch": 2.05,
      "learning_rate": 6.375779162956367e-05,
      "loss": 0.5055,
      "step": 767
    },
    {
      "epoch": 2.05,
      "learning_rate": 6.357969723953696e-05,
      "loss": 0.4828,
      "step": 768
    },
    {
      "epoch": 2.05,
      "learning_rate": 6.340160284951025e-05,
      "loss": 0.5674,
      "step": 769
    },
    {
      "epoch": 2.05,
      "learning_rate": 6.322350845948353e-05,
      "loss": 0.5898,
      "step": 770
    },
    {
      "epoch": 2.06,
      "learning_rate": 6.304541406945681e-05,
      "loss": 0.3173,
      "step": 771
    },
    {
      "epoch": 2.06,
      "learning_rate": 6.286731967943011e-05,
      "loss": 0.6083,
      "step": 772
    },
    {
      "epoch": 2.06,
      "learning_rate": 6.268922528940338e-05,
      "loss": 0.2222,
      "step": 773
    },
    {
      "epoch": 2.06,
      "learning_rate": 6.251113089937666e-05,
      "loss": 0.4865,
      "step": 774
    },
    {
      "epoch": 2.07,
      "learning_rate": 6.233303650934996e-05,
      "loss": 0.5414,
      "step": 775
    },
    {
      "epoch": 2.07,
      "learning_rate": 6.215494211932324e-05,
      "loss": 0.6213,
      "step": 776
    },
    {
      "epoch": 2.07,
      "learning_rate": 6.197684772929653e-05,
      "loss": 0.4933,
      "step": 777
    },
    {
      "epoch": 2.07,
      "learning_rate": 6.179875333926982e-05,
      "loss": 0.4604,
      "step": 778
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.162065894924311e-05,
      "loss": 0.5353,
      "step": 779
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.144256455921639e-05,
      "loss": 0.5483,
      "step": 780
    },
    {
      "epoch": 2.08,
      "eval_loss": 0.7184942364692688,
      "eval_runtime": 3070.429,
      "eval_samples_per_second": 0.977,
      "eval_steps_per_second": 0.061,
      "step": 780
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.126447016918968e-05,
      "loss": 0.5889,
      "step": 781
    },
    {
      "epoch": 2.09,
      "learning_rate": 6.108637577916296e-05,
      "loss": 0.5588,
      "step": 782
    },
    {
      "epoch": 2.09,
      "learning_rate": 6.090828138913625e-05,
      "loss": 0.2642,
      "step": 783
    },
    {
      "epoch": 2.09,
      "learning_rate": 6.0730186999109526e-05,
      "loss": 0.6108,
      "step": 784
    },
    {
      "epoch": 2.09,
      "learning_rate": 6.055209260908282e-05,
      "loss": 0.5766,
      "step": 785
    },
    {
      "epoch": 2.1,
      "learning_rate": 6.0373998219056106e-05,
      "loss": 0.5958,
      "step": 786
    },
    {
      "epoch": 2.1,
      "learning_rate": 6.019590382902939e-05,
      "loss": 0.4791,
      "step": 787
    },
    {
      "epoch": 2.1,
      "learning_rate": 6.001780943900267e-05,
      "loss": 0.6763,
      "step": 788
    },
    {
      "epoch": 2.1,
      "learning_rate": 5.9839715048975963e-05,
      "loss": 0.2521,
      "step": 789
    },
    {
      "epoch": 2.11,
      "learning_rate": 5.966162065894925e-05,
      "loss": 0.6006,
      "step": 790
    },
    {
      "epoch": 2.11,
      "learning_rate": 5.948352626892253e-05,
      "loss": 0.493,
      "step": 791
    },
    {
      "epoch": 2.11,
      "learning_rate": 5.930543187889582e-05,
      "loss": 0.4216,
      "step": 792
    },
    {
      "epoch": 2.11,
      "learning_rate": 5.9127337488869104e-05,
      "loss": 0.2425,
      "step": 793
    },
    {
      "epoch": 2.12,
      "learning_rate": 5.894924309884239e-05,
      "loss": 0.4613,
      "step": 794
    },
    {
      "epoch": 2.12,
      "learning_rate": 5.877114870881567e-05,
      "loss": 0.5102,
      "step": 795
    },
    {
      "epoch": 2.12,
      "learning_rate": 5.859305431878896e-05,
      "loss": 0.2585,
      "step": 796
    },
    {
      "epoch": 2.13,
      "learning_rate": 5.8414959928762245e-05,
      "loss": 0.5613,
      "step": 797
    },
    {
      "epoch": 2.13,
      "learning_rate": 5.823686553873553e-05,
      "loss": 0.5372,
      "step": 798
    },
    {
      "epoch": 2.13,
      "learning_rate": 5.8058771148708826e-05,
      "loss": 0.2502,
      "step": 799
    },
    {
      "epoch": 2.13,
      "learning_rate": 5.788067675868211e-05,
      "loss": 0.5299,
      "step": 800
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.7702582368655386e-05,
      "loss": 0.5208,
      "step": 801
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.752448797862867e-05,
      "loss": 0.6105,
      "step": 802
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.7346393588601966e-05,
      "loss": 0.4572,
      "step": 803
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.716829919857525e-05,
      "loss": 0.4496,
      "step": 804
    },
    {
      "epoch": 2.15,
      "learning_rate": 5.6990204808548533e-05,
      "loss": 0.6963,
      "step": 805
    },
    {
      "epoch": 2.15,
      "learning_rate": 5.6812110418521824e-05,
      "loss": 0.4791,
      "step": 806
    },
    {
      "epoch": 2.15,
      "learning_rate": 5.663401602849511e-05,
      "loss": 0.5877,
      "step": 807
    },
    {
      "epoch": 2.15,
      "learning_rate": 5.645592163846839e-05,
      "loss": 0.5969,
      "step": 808
    },
    {
      "epoch": 2.16,
      "learning_rate": 5.6277827248441674e-05,
      "loss": 0.6696,
      "step": 809
    },
    {
      "epoch": 2.16,
      "learning_rate": 5.6099732858414964e-05,
      "loss": 0.6348,
      "step": 810
    },
    {
      "epoch": 2.16,
      "learning_rate": 5.592163846838825e-05,
      "loss": 0.5062,
      "step": 811
    },
    {
      "epoch": 2.17,
      "learning_rate": 5.574354407836153e-05,
      "loss": 0.4852,
      "step": 812
    },
    {
      "epoch": 2.17,
      "learning_rate": 5.556544968833483e-05,
      "loss": 0.2839,
      "step": 813
    },
    {
      "epoch": 2.17,
      "learning_rate": 5.5387355298308105e-05,
      "loss": 0.3634,
      "step": 814
    },
    {
      "epoch": 2.17,
      "learning_rate": 5.520926090828139e-05,
      "loss": 0.4404,
      "step": 815
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.503116651825467e-05,
      "loss": 0.5002,
      "step": 816
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.485307212822797e-05,
      "loss": 0.4835,
      "step": 817
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.467497773820125e-05,
      "loss": 0.0,
      "step": 818
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.449688334817453e-05,
      "loss": 0.5531,
      "step": 819
    },
    {
      "epoch": 2.19,
      "learning_rate": 5.4318788958147827e-05,
      "loss": 0.5685,
      "step": 820
    },
    {
      "epoch": 2.19,
      "learning_rate": 5.414069456812111e-05,
      "loss": 0.6242,
      "step": 821
    },
    {
      "epoch": 2.19,
      "learning_rate": 5.3962600178094394e-05,
      "loss": 0.3086,
      "step": 822
    },
    {
      "epoch": 2.19,
      "learning_rate": 5.378450578806768e-05,
      "loss": 0.5342,
      "step": 823
    },
    {
      "epoch": 2.2,
      "learning_rate": 5.360641139804097e-05,
      "loss": 0.6173,
      "step": 824
    },
    {
      "epoch": 2.2,
      "learning_rate": 5.342831700801425e-05,
      "loss": 0.5492,
      "step": 825
    },
    {
      "epoch": 2.2,
      "learning_rate": 5.3250222617987534e-05,
      "loss": 0.7154,
      "step": 826
    },
    {
      "epoch": 2.21,
      "learning_rate": 5.3072128227960825e-05,
      "loss": 0.4763,
      "step": 827
    },
    {
      "epoch": 2.21,
      "learning_rate": 5.289403383793411e-05,
      "loss": 0.5074,
      "step": 828
    },
    {
      "epoch": 2.21,
      "learning_rate": 5.271593944790739e-05,
      "loss": 0.6183,
      "step": 829
    },
    {
      "epoch": 2.21,
      "learning_rate": 5.2537845057880675e-05,
      "loss": 0.3336,
      "step": 830
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.2359750667853965e-05,
      "loss": 0.3096,
      "step": 831
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.218165627782725e-05,
      "loss": 0.5492,
      "step": 832
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.200356188780053e-05,
      "loss": 0.5015,
      "step": 833
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.182546749777383e-05,
      "loss": 0.2283,
      "step": 834
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.164737310774711e-05,
      "loss": 0.6955,
      "step": 835
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.146927871772039e-05,
      "loss": 0.5242,
      "step": 836
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.129118432769367e-05,
      "loss": 0.5285,
      "step": 837
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.111308993766697e-05,
      "loss": 0.6641,
      "step": 838
    },
    {
      "epoch": 2.24,
      "learning_rate": 5.0934995547640254e-05,
      "loss": 0.4676,
      "step": 839
    },
    {
      "epoch": 2.24,
      "learning_rate": 5.075690115761354e-05,
      "loss": 0.4343,
      "step": 840
    },
    {
      "epoch": 2.24,
      "learning_rate": 5.057880676758683e-05,
      "loss": 0.6591,
      "step": 841
    },
    {
      "epoch": 2.25,
      "learning_rate": 5.040071237756011e-05,
      "loss": 0.7085,
      "step": 842
    },
    {
      "epoch": 2.25,
      "learning_rate": 5.0222617987533395e-05,
      "loss": 0.4633,
      "step": 843
    },
    {
      "epoch": 2.25,
      "learning_rate": 5.004452359750668e-05,
      "loss": 0.2814,
      "step": 844
    },
    {
      "epoch": 2.25,
      "learning_rate": 4.986642920747996e-05,
      "loss": 0.6218,
      "step": 845
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.968833481745325e-05,
      "loss": 0.6177,
      "step": 846
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.951024042742654e-05,
      "loss": 0.3615,
      "step": 847
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.9332146037399826e-05,
      "loss": 0.4262,
      "step": 848
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.915405164737311e-05,
      "loss": 0.5926,
      "step": 849
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.897595725734639e-05,
      "loss": 0.5194,
      "step": 850
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.879786286731968e-05,
      "loss": 0.7846,
      "step": 851
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.8619768477292966e-05,
      "loss": 0.6291,
      "step": 852
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.844167408726625e-05,
      "loss": 0.5293,
      "step": 853
    },
    {
      "epoch": 2.28,
      "learning_rate": 4.826357969723954e-05,
      "loss": 0.7641,
      "step": 854
    },
    {
      "epoch": 2.28,
      "learning_rate": 4.8085485307212824e-05,
      "loss": 0.5638,
      "step": 855
    },
    {
      "epoch": 2.28,
      "learning_rate": 4.7907390917186114e-05,
      "loss": 0.4537,
      "step": 856
    },
    {
      "epoch": 2.29,
      "learning_rate": 4.77292965271594e-05,
      "loss": 0.5004,
      "step": 857
    },
    {
      "epoch": 2.29,
      "learning_rate": 4.755120213713268e-05,
      "loss": 0.5058,
      "step": 858
    },
    {
      "epoch": 2.29,
      "learning_rate": 4.7373107747105965e-05,
      "loss": 0.6613,
      "step": 859
    },
    {
      "epoch": 2.29,
      "learning_rate": 4.7195013357079255e-05,
      "loss": 0.5536,
      "step": 860
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.7016918967052545e-05,
      "loss": 0.2145,
      "step": 861
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.683882457702582e-05,
      "loss": 0.6103,
      "step": 862
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.666073018699911e-05,
      "loss": 0.2994,
      "step": 863
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.6482635796972396e-05,
      "loss": 0.2918,
      "step": 864
    },
    {
      "epoch": 2.31,
      "learning_rate": 4.6304541406945686e-05,
      "loss": 0.4479,
      "step": 865
    },
    {
      "epoch": 2.31,
      "learning_rate": 4.612644701691897e-05,
      "loss": 0.5615,
      "step": 866
    },
    {
      "epoch": 2.31,
      "learning_rate": 4.594835262689225e-05,
      "loss": 0.5611,
      "step": 867
    },
    {
      "epoch": 2.31,
      "learning_rate": 4.577025823686554e-05,
      "loss": 0.4812,
      "step": 868
    },
    {
      "epoch": 2.32,
      "learning_rate": 4.559216384683883e-05,
      "loss": 0.4333,
      "step": 869
    },
    {
      "epoch": 2.32,
      "learning_rate": 4.541406945681212e-05,
      "loss": 0.6103,
      "step": 870
    },
    {
      "epoch": 2.32,
      "learning_rate": 4.5235975066785394e-05,
      "loss": 0.4906,
      "step": 871
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.5057880676758684e-05,
      "loss": 0.5529,
      "step": 872
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.487978628673197e-05,
      "loss": 0.6428,
      "step": 873
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.470169189670526e-05,
      "loss": 0.5908,
      "step": 874
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.452359750667854e-05,
      "loss": 0.7357,
      "step": 875
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.4345503116651825e-05,
      "loss": 0.5283,
      "step": 876
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.4167408726625115e-05,
      "loss": 0.5263,
      "step": 877
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.39893143365984e-05,
      "loss": 0.5833,
      "step": 878
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.381121994657169e-05,
      "loss": 0.4495,
      "step": 879
    },
    {
      "epoch": 2.35,
      "learning_rate": 4.363312555654497e-05,
      "loss": 0.5486,
      "step": 880
    },
    {
      "epoch": 2.35,
      "learning_rate": 4.3455031166518256e-05,
      "loss": 0.4974,
      "step": 881
    },
    {
      "epoch": 2.35,
      "learning_rate": 4.3276936776491546e-05,
      "loss": 0.5267,
      "step": 882
    },
    {
      "epoch": 2.35,
      "learning_rate": 4.309884238646483e-05,
      "loss": 0.5541,
      "step": 883
    },
    {
      "epoch": 2.36,
      "learning_rate": 4.292074799643811e-05,
      "loss": 0.5155,
      "step": 884
    },
    {
      "epoch": 2.36,
      "learning_rate": 4.27426536064114e-05,
      "loss": 0.7037,
      "step": 885
    },
    {
      "epoch": 2.36,
      "learning_rate": 4.256455921638469e-05,
      "loss": 0.4534,
      "step": 886
    },
    {
      "epoch": 2.37,
      "learning_rate": 4.238646482635798e-05,
      "loss": 0.315,
      "step": 887
    },
    {
      "epoch": 2.37,
      "learning_rate": 4.2208370436331254e-05,
      "loss": 0.4836,
      "step": 888
    },
    {
      "epoch": 2.37,
      "learning_rate": 4.2030276046304544e-05,
      "loss": 0.5279,
      "step": 889
    },
    {
      "epoch": 2.37,
      "learning_rate": 4.185218165627783e-05,
      "loss": 0.4331,
      "step": 890
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.167408726625112e-05,
      "loss": 0.2976,
      "step": 891
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.14959928762244e-05,
      "loss": 0.4118,
      "step": 892
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.1317898486197685e-05,
      "loss": 0.4208,
      "step": 893
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.1139804096170975e-05,
      "loss": 0.5812,
      "step": 894
    },
    {
      "epoch": 2.39,
      "learning_rate": 4.096170970614426e-05,
      "loss": 0.3178,
      "step": 895
    },
    {
      "epoch": 2.39,
      "learning_rate": 4.078361531611755e-05,
      "loss": 0.0,
      "step": 896
    },
    {
      "epoch": 2.39,
      "learning_rate": 4.0605520926090826e-05,
      "loss": 0.5466,
      "step": 897
    },
    {
      "epoch": 2.39,
      "learning_rate": 4.0427426536064116e-05,
      "loss": 0.5901,
      "step": 898
    },
    {
      "epoch": 2.4,
      "learning_rate": 4.02493321460374e-05,
      "loss": 0.4959,
      "step": 899
    },
    {
      "epoch": 2.4,
      "learning_rate": 4.007123775601069e-05,
      "loss": 0.4362,
      "step": 900
    },
    {
      "epoch": 2.4,
      "learning_rate": 3.989314336598397e-05,
      "loss": 0.651,
      "step": 901
    },
    {
      "epoch": 2.41,
      "learning_rate": 3.971504897595726e-05,
      "loss": 0.4988,
      "step": 902
    },
    {
      "epoch": 2.41,
      "learning_rate": 3.953695458593055e-05,
      "loss": 0.4345,
      "step": 903
    },
    {
      "epoch": 2.41,
      "learning_rate": 3.935886019590383e-05,
      "loss": 0.5049,
      "step": 904
    },
    {
      "epoch": 2.41,
      "learning_rate": 3.918076580587712e-05,
      "loss": 0.5505,
      "step": 905
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.90026714158504e-05,
      "loss": 0.543,
      "step": 906
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.882457702582369e-05,
      "loss": 0.5359,
      "step": 907
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.864648263579698e-05,
      "loss": 0.4317,
      "step": 908
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.846838824577026e-05,
      "loss": 0.4648,
      "step": 909
    },
    {
      "epoch": 2.43,
      "learning_rate": 3.8290293855743545e-05,
      "loss": 0.2252,
      "step": 910
    },
    {
      "epoch": 2.43,
      "learning_rate": 3.811219946571683e-05,
      "loss": 0.6439,
      "step": 911
    },
    {
      "epoch": 2.43,
      "learning_rate": 3.793410507569012e-05,
      "loss": 0.5382,
      "step": 912
    },
    {
      "epoch": 2.43,
      "learning_rate": 3.77560106856634e-05,
      "loss": 0.4928,
      "step": 913
    },
    {
      "epoch": 2.44,
      "learning_rate": 3.7577916295636686e-05,
      "loss": 0.4914,
      "step": 914
    },
    {
      "epoch": 2.44,
      "learning_rate": 3.7399821905609976e-05,
      "loss": 0.5281,
      "step": 915
    },
    {
      "epoch": 2.44,
      "learning_rate": 3.722172751558326e-05,
      "loss": 0.5426,
      "step": 916
    },
    {
      "epoch": 2.45,
      "learning_rate": 3.704363312555655e-05,
      "loss": 0.4833,
      "step": 917
    },
    {
      "epoch": 2.45,
      "learning_rate": 3.6865538735529834e-05,
      "loss": 0.5073,
      "step": 918
    },
    {
      "epoch": 2.45,
      "learning_rate": 3.668744434550312e-05,
      "loss": 0.6785,
      "step": 919
    },
    {
      "epoch": 2.45,
      "learning_rate": 3.65093499554764e-05,
      "loss": 0.5446,
      "step": 920
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.633125556544969e-05,
      "loss": 0.6372,
      "step": 921
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.615316117542298e-05,
      "loss": 0.6244,
      "step": 922
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.597506678539626e-05,
      "loss": 0.6706,
      "step": 923
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.579697239536955e-05,
      "loss": 0.4218,
      "step": 924
    },
    {
      "epoch": 2.47,
      "learning_rate": 3.561887800534283e-05,
      "loss": 0.6145,
      "step": 925
    },
    {
      "epoch": 2.47,
      "learning_rate": 3.544078361531612e-05,
      "loss": 0.4184,
      "step": 926
    },
    {
      "epoch": 2.47,
      "learning_rate": 3.5262689225289405e-05,
      "loss": 0.5874,
      "step": 927
    },
    {
      "epoch": 2.47,
      "learning_rate": 3.508459483526269e-05,
      "loss": 0.5598,
      "step": 928
    },
    {
      "epoch": 2.48,
      "learning_rate": 3.490650044523598e-05,
      "loss": 0.5509,
      "step": 929
    },
    {
      "epoch": 2.48,
      "learning_rate": 3.472840605520926e-05,
      "loss": 0.456,
      "step": 930
    },
    {
      "epoch": 2.48,
      "learning_rate": 3.455031166518255e-05,
      "loss": 0.2864,
      "step": 931
    },
    {
      "epoch": 2.49,
      "learning_rate": 3.437221727515583e-05,
      "loss": 0.2309,
      "step": 932
    },
    {
      "epoch": 2.49,
      "learning_rate": 3.419412288512912e-05,
      "loss": 0.4592,
      "step": 933
    },
    {
      "epoch": 2.49,
      "learning_rate": 3.4016028495102404e-05,
      "loss": 0.6289,
      "step": 934
    },
    {
      "epoch": 2.49,
      "learning_rate": 3.3837934105075694e-05,
      "loss": 0.5241,
      "step": 935
    },
    {
      "epoch": 2.5,
      "learning_rate": 3.365983971504898e-05,
      "loss": 0.5452,
      "step": 936
    },
    {
      "epoch": 2.5,
      "eval_loss": 0.7189126014709473,
      "eval_runtime": 3073.0668,
      "eval_samples_per_second": 0.976,
      "eval_steps_per_second": 0.061,
      "step": 936
    },
    {
      "epoch": 2.5,
      "learning_rate": 3.348174532502226e-05,
      "loss": 0.4962,
      "step": 937
    },
    {
      "epoch": 2.5,
      "learning_rate": 3.330365093499555e-05,
      "loss": 0.4951,
      "step": 938
    },
    {
      "epoch": 2.5,
      "learning_rate": 3.3125556544968835e-05,
      "loss": 0.7431,
      "step": 939
    },
    {
      "epoch": 2.51,
      "learning_rate": 3.294746215494212e-05,
      "loss": 0.4837,
      "step": 940
    },
    {
      "epoch": 2.51,
      "learning_rate": 3.27693677649154e-05,
      "loss": 0.3271,
      "step": 941
    },
    {
      "epoch": 2.51,
      "learning_rate": 3.259127337488869e-05,
      "loss": 0.5759,
      "step": 942
    },
    {
      "epoch": 2.51,
      "learning_rate": 3.241317898486198e-05,
      "loss": 0.3889,
      "step": 943
    },
    {
      "epoch": 2.52,
      "learning_rate": 3.2235084594835266e-05,
      "loss": 0.5234,
      "step": 944
    },
    {
      "epoch": 2.52,
      "learning_rate": 3.205699020480855e-05,
      "loss": 0.5873,
      "step": 945
    },
    {
      "epoch": 2.52,
      "learning_rate": 3.187889581478183e-05,
      "loss": 0.4699,
      "step": 946
    },
    {
      "epoch": 2.53,
      "learning_rate": 3.170080142475512e-05,
      "loss": 0.4407,
      "step": 947
    },
    {
      "epoch": 2.53,
      "learning_rate": 3.1522707034728406e-05,
      "loss": 0.4821,
      "step": 948
    },
    {
      "epoch": 2.53,
      "learning_rate": 3.134461264470169e-05,
      "loss": 0.4958,
      "step": 949
    },
    {
      "epoch": 2.53,
      "learning_rate": 3.116651825467498e-05,
      "loss": 0.5546,
      "step": 950
    },
    {
      "epoch": 2.54,
      "learning_rate": 3.0988423864648264e-05,
      "loss": 0.4307,
      "step": 951
    },
    {
      "epoch": 2.54,
      "learning_rate": 3.0810329474621554e-05,
      "loss": 0.461,
      "step": 952
    },
    {
      "epoch": 2.54,
      "learning_rate": 3.063223508459484e-05,
      "loss": 0.2707,
      "step": 953
    },
    {
      "epoch": 2.54,
      "learning_rate": 3.0454140694568124e-05,
      "loss": 0.4925,
      "step": 954
    },
    {
      "epoch": 2.55,
      "learning_rate": 3.027604630454141e-05,
      "loss": 0.5388,
      "step": 955
    },
    {
      "epoch": 2.55,
      "learning_rate": 3.0097951914514695e-05,
      "loss": 0.0,
      "step": 956
    },
    {
      "epoch": 2.55,
      "learning_rate": 2.9919857524487982e-05,
      "loss": 0.4366,
      "step": 957
    },
    {
      "epoch": 2.55,
      "learning_rate": 2.9741763134461265e-05,
      "loss": 0.6114,
      "step": 958
    },
    {
      "epoch": 2.56,
      "learning_rate": 2.9563668744434552e-05,
      "loss": 0.2699,
      "step": 959
    },
    {
      "epoch": 2.56,
      "learning_rate": 2.9385574354407836e-05,
      "loss": 0.5328,
      "step": 960
    },
    {
      "epoch": 2.56,
      "learning_rate": 2.9207479964381123e-05,
      "loss": 0.2477,
      "step": 961
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.9029385574354413e-05,
      "loss": 0.0,
      "step": 962
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.8851291184327693e-05,
      "loss": 0.5676,
      "step": 963
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.8673196794300983e-05,
      "loss": 0.4322,
      "step": 964
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.8495102404274267e-05,
      "loss": 0.7527,
      "step": 965
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.8317008014247554e-05,
      "loss": 0.4511,
      "step": 966
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.8138913624220837e-05,
      "loss": 0.4393,
      "step": 967
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.7960819234194124e-05,
      "loss": 0.6151,
      "step": 968
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.7782724844167414e-05,
      "loss": 0.5711,
      "step": 969
    },
    {
      "epoch": 2.59,
      "learning_rate": 2.7604630454140694e-05,
      "loss": 0.562,
      "step": 970
    },
    {
      "epoch": 2.59,
      "learning_rate": 2.7426536064113985e-05,
      "loss": 0.4842,
      "step": 971
    },
    {
      "epoch": 2.59,
      "learning_rate": 2.7248441674087265e-05,
      "loss": 0.5702,
      "step": 972
    },
    {
      "epoch": 2.59,
      "learning_rate": 2.7070347284060555e-05,
      "loss": 0.0,
      "step": 973
    },
    {
      "epoch": 2.6,
      "learning_rate": 2.689225289403384e-05,
      "loss": 0.0,
      "step": 974
    },
    {
      "epoch": 2.6,
      "learning_rate": 2.6714158504007125e-05,
      "loss": 0.3925,
      "step": 975
    },
    {
      "epoch": 2.6,
      "learning_rate": 2.6536064113980412e-05,
      "loss": 0.2426,
      "step": 976
    },
    {
      "epoch": 2.61,
      "learning_rate": 2.6357969723953696e-05,
      "loss": 0.5499,
      "step": 977
    },
    {
      "epoch": 2.61,
      "learning_rate": 2.6179875333926983e-05,
      "loss": 0.5658,
      "step": 978
    },
    {
      "epoch": 2.61,
      "learning_rate": 2.6001780943900266e-05,
      "loss": 0.4884,
      "step": 979
    },
    {
      "epoch": 2.61,
      "learning_rate": 2.5823686553873557e-05,
      "loss": 0.6483,
      "step": 980
    },
    {
      "epoch": 2.62,
      "learning_rate": 2.5645592163846837e-05,
      "loss": 0.6559,
      "step": 981
    },
    {
      "epoch": 2.62,
      "learning_rate": 2.5467497773820127e-05,
      "loss": 0.5516,
      "step": 982
    },
    {
      "epoch": 2.62,
      "learning_rate": 2.5289403383793414e-05,
      "loss": 0.4207,
      "step": 983
    },
    {
      "epoch": 2.62,
      "learning_rate": 2.5111308993766697e-05,
      "loss": 0.5948,
      "step": 984
    },
    {
      "epoch": 2.63,
      "learning_rate": 2.493321460373998e-05,
      "loss": 0.5739,
      "step": 985
    },
    {
      "epoch": 2.63,
      "learning_rate": 2.475512021371327e-05,
      "loss": 0.4825,
      "step": 986
    },
    {
      "epoch": 2.63,
      "learning_rate": 2.4577025823686555e-05,
      "loss": 0.5103,
      "step": 987
    },
    {
      "epoch": 2.63,
      "learning_rate": 2.439893143365984e-05,
      "loss": 0.3186,
      "step": 988
    },
    {
      "epoch": 2.64,
      "learning_rate": 2.4220837043633125e-05,
      "loss": 0.4993,
      "step": 989
    },
    {
      "epoch": 2.64,
      "learning_rate": 2.4042742653606412e-05,
      "loss": 0.2724,
      "step": 990
    },
    {
      "epoch": 2.64,
      "learning_rate": 2.38646482635797e-05,
      "loss": 0.4808,
      "step": 991
    },
    {
      "epoch": 2.65,
      "learning_rate": 2.3686553873552982e-05,
      "loss": 0.5503,
      "step": 992
    },
    {
      "epoch": 2.65,
      "learning_rate": 2.3508459483526273e-05,
      "loss": 0.6419,
      "step": 993
    },
    {
      "epoch": 2.65,
      "learning_rate": 2.3330365093499556e-05,
      "loss": 0.7394,
      "step": 994
    },
    {
      "epoch": 2.65,
      "learning_rate": 2.3152270703472843e-05,
      "loss": 0.5237,
      "step": 995
    },
    {
      "epoch": 2.66,
      "learning_rate": 2.2974176313446126e-05,
      "loss": 0.448,
      "step": 996
    },
    {
      "epoch": 2.66,
      "learning_rate": 2.2796081923419413e-05,
      "loss": 0.6442,
      "step": 997
    },
    {
      "epoch": 2.66,
      "learning_rate": 2.2617987533392697e-05,
      "loss": 0.5423,
      "step": 998
    },
    {
      "epoch": 2.66,
      "learning_rate": 2.2439893143365984e-05,
      "loss": 0.5845,
      "step": 999
    },
    {
      "epoch": 2.67,
      "learning_rate": 2.226179875333927e-05,
      "loss": 0.4551,
      "step": 1000
    },
    {
      "epoch": 2.67,
      "learning_rate": 2.2083704363312558e-05,
      "loss": 0.4767,
      "step": 1001
    },
    {
      "epoch": 2.67,
      "learning_rate": 2.1905609973285844e-05,
      "loss": 0.6081,
      "step": 1002
    },
    {
      "epoch": 2.67,
      "learning_rate": 2.1727515583259128e-05,
      "loss": 0.3134,
      "step": 1003
    },
    {
      "epoch": 2.68,
      "learning_rate": 2.1549421193232415e-05,
      "loss": 0.5865,
      "step": 1004
    },
    {
      "epoch": 2.68,
      "learning_rate": 2.13713268032057e-05,
      "loss": 0.1635,
      "step": 1005
    },
    {
      "epoch": 2.68,
      "learning_rate": 2.119323241317899e-05,
      "loss": 0.5114,
      "step": 1006
    },
    {
      "epoch": 2.69,
      "learning_rate": 2.1015138023152272e-05,
      "loss": 0.585,
      "step": 1007
    },
    {
      "epoch": 2.69,
      "learning_rate": 2.083704363312556e-05,
      "loss": 0.5333,
      "step": 1008
    },
    {
      "epoch": 2.69,
      "learning_rate": 2.0658949243098843e-05,
      "loss": 0.2309,
      "step": 1009
    },
    {
      "epoch": 2.69,
      "learning_rate": 2.048085485307213e-05,
      "loss": 0.7229,
      "step": 1010
    },
    {
      "epoch": 2.7,
      "learning_rate": 2.0302760463045413e-05,
      "loss": 0.3001,
      "step": 1011
    },
    {
      "epoch": 2.7,
      "learning_rate": 2.01246660730187e-05,
      "loss": 0.5959,
      "step": 1012
    },
    {
      "epoch": 2.7,
      "learning_rate": 1.9946571682991987e-05,
      "loss": 0.7011,
      "step": 1013
    },
    {
      "epoch": 2.7,
      "learning_rate": 1.9768477292965274e-05,
      "loss": 0.5569,
      "step": 1014
    },
    {
      "epoch": 2.71,
      "learning_rate": 1.959038290293856e-05,
      "loss": 0.2309,
      "step": 1015
    },
    {
      "epoch": 2.71,
      "learning_rate": 1.9412288512911844e-05,
      "loss": 0.1953,
      "step": 1016
    },
    {
      "epoch": 2.71,
      "learning_rate": 1.923419412288513e-05,
      "loss": 0.6111,
      "step": 1017
    },
    {
      "epoch": 2.71,
      "learning_rate": 1.9056099732858414e-05,
      "loss": 0.53,
      "step": 1018
    },
    {
      "epoch": 2.72,
      "learning_rate": 1.88780053428317e-05,
      "loss": 0.4797,
      "step": 1019
    },
    {
      "epoch": 2.72,
      "learning_rate": 1.8699910952804988e-05,
      "loss": 0.5537,
      "step": 1020
    },
    {
      "epoch": 2.72,
      "learning_rate": 1.8521816562778275e-05,
      "loss": 0.5335,
      "step": 1021
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.834372217275156e-05,
      "loss": 0.2199,
      "step": 1022
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.8165627782724845e-05,
      "loss": 0.205,
      "step": 1023
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.798753339269813e-05,
      "loss": 0.5601,
      "step": 1024
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.7809439002671416e-05,
      "loss": 0.4996,
      "step": 1025
    },
    {
      "epoch": 2.74,
      "learning_rate": 1.7631344612644703e-05,
      "loss": 0.5524,
      "step": 1026
    },
    {
      "epoch": 2.74,
      "learning_rate": 1.745325022261799e-05,
      "loss": 0.3372,
      "step": 1027
    },
    {
      "epoch": 2.74,
      "learning_rate": 1.7275155832591277e-05,
      "loss": 0.5229,
      "step": 1028
    },
    {
      "epoch": 2.74,
      "learning_rate": 1.709706144256456e-05,
      "loss": 0.4927,
      "step": 1029
    },
    {
      "epoch": 2.75,
      "learning_rate": 1.6918967052537847e-05,
      "loss": 0.4765,
      "step": 1030
    },
    {
      "epoch": 2.75,
      "learning_rate": 1.674087266251113e-05,
      "loss": 0.5663,
      "step": 1031
    },
    {
      "epoch": 2.75,
      "learning_rate": 1.6562778272484417e-05,
      "loss": 0.6083,
      "step": 1032
    },
    {
      "epoch": 2.75,
      "learning_rate": 1.63846838824577e-05,
      "loss": 0.4604,
      "step": 1033
    },
    {
      "epoch": 2.76,
      "learning_rate": 1.620658949243099e-05,
      "loss": 0.4415,
      "step": 1034
    },
    {
      "epoch": 2.76,
      "learning_rate": 1.6028495102404275e-05,
      "loss": 0.1771,
      "step": 1035
    },
    {
      "epoch": 2.76,
      "learning_rate": 1.585040071237756e-05,
      "loss": 0.2848,
      "step": 1036
    },
    {
      "epoch": 2.77,
      "learning_rate": 1.5672306322350845e-05,
      "loss": 0.6078,
      "step": 1037
    },
    {
      "epoch": 2.77,
      "learning_rate": 1.5494211932324132e-05,
      "loss": 0.5374,
      "step": 1038
    },
    {
      "epoch": 2.77,
      "learning_rate": 1.531611754229742e-05,
      "loss": 0.5114,
      "step": 1039
    },
    {
      "epoch": 2.77,
      "learning_rate": 1.5138023152270706e-05,
      "loss": 0.5361,
      "step": 1040
    },
    {
      "epoch": 2.78,
      "learning_rate": 1.4959928762243991e-05,
      "loss": 0.3074,
      "step": 1041
    },
    {
      "epoch": 2.78,
      "learning_rate": 1.4781834372217276e-05,
      "loss": 0.5281,
      "step": 1042
    },
    {
      "epoch": 2.78,
      "learning_rate": 1.4603739982190561e-05,
      "loss": 0.2628,
      "step": 1043
    },
    {
      "epoch": 2.78,
      "learning_rate": 1.4425645592163846e-05,
      "loss": 0.6858,
      "step": 1044
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.4247551202137133e-05,
      "loss": 0.5042,
      "step": 1045
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.4069456812110419e-05,
      "loss": 0.539,
      "step": 1046
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.3891362422083707e-05,
      "loss": 0.4862,
      "step": 1047
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.3713268032056992e-05,
      "loss": 0.2817,
      "step": 1048
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.3535173642030278e-05,
      "loss": 0.6027,
      "step": 1049
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.3357079252003563e-05,
      "loss": 0.4997,
      "step": 1050
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.3178984861976848e-05,
      "loss": 0.6057,
      "step": 1051
    },
    {
      "epoch": 2.81,
      "learning_rate": 1.3000890471950133e-05,
      "loss": 0.6287,
      "step": 1052
    },
    {
      "epoch": 2.81,
      "learning_rate": 1.2822796081923418e-05,
      "loss": 0.5216,
      "step": 1053
    },
    {
      "epoch": 2.81,
      "learning_rate": 1.2644701691896707e-05,
      "loss": 0.5183,
      "step": 1054
    },
    {
      "epoch": 2.81,
      "learning_rate": 1.246660730186999e-05,
      "loss": 0.5827,
      "step": 1055
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.2288512911843277e-05,
      "loss": 0.7063,
      "step": 1056
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.2110418521816562e-05,
      "loss": 0.5105,
      "step": 1057
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.193232413178985e-05,
      "loss": 0.5323,
      "step": 1058
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.1754229741763136e-05,
      "loss": 0.6138,
      "step": 1059
    },
    {
      "epoch": 2.83,
      "learning_rate": 1.1576135351736421e-05,
      "loss": 0.3587,
      "step": 1060
    },
    {
      "epoch": 2.83,
      "learning_rate": 1.1398040961709707e-05,
      "loss": 0.3221,
      "step": 1061
    },
    {
      "epoch": 2.83,
      "learning_rate": 1.1219946571682992e-05,
      "loss": 0.545,
      "step": 1062
    },
    {
      "epoch": 2.83,
      "learning_rate": 1.1041852181656279e-05,
      "loss": 0.5451,
      "step": 1063
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.0863757791629564e-05,
      "loss": 0.4481,
      "step": 1064
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.068566340160285e-05,
      "loss": 0.5007,
      "step": 1065
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.0507569011576136e-05,
      "loss": 0.7057,
      "step": 1066
    },
    {
      "epoch": 2.85,
      "learning_rate": 1.0329474621549421e-05,
      "loss": 0.7881,
      "step": 1067
    },
    {
      "epoch": 2.85,
      "learning_rate": 1.0151380231522706e-05,
      "loss": 0.4972,
      "step": 1068
    },
    {
      "epoch": 2.85,
      "learning_rate": 9.973285841495993e-06,
      "loss": 0.6574,
      "step": 1069
    },
    {
      "epoch": 2.85,
      "learning_rate": 9.79519145146928e-06,
      "loss": 0.6185,
      "step": 1070
    },
    {
      "epoch": 2.86,
      "learning_rate": 9.617097061442565e-06,
      "loss": 0.4693,
      "step": 1071
    },
    {
      "epoch": 2.86,
      "learning_rate": 9.43900267141585e-06,
      "loss": 0.5833,
      "step": 1072
    },
    {
      "epoch": 2.86,
      "learning_rate": 9.260908281389138e-06,
      "loss": 0.5996,
      "step": 1073
    },
    {
      "epoch": 2.86,
      "learning_rate": 9.082813891362423e-06,
      "loss": 0.7077,
      "step": 1074
    },
    {
      "epoch": 2.87,
      "learning_rate": 8.904719501335708e-06,
      "loss": 0.5141,
      "step": 1075
    },
    {
      "epoch": 2.87,
      "learning_rate": 8.726625111308995e-06,
      "loss": 0.2115,
      "step": 1076
    },
    {
      "epoch": 2.87,
      "learning_rate": 8.54853072128228e-06,
      "loss": 0.6349,
      "step": 1077
    },
    {
      "epoch": 2.87,
      "learning_rate": 8.370436331255565e-06,
      "loss": 0.0,
      "step": 1078
    },
    {
      "epoch": 2.88,
      "learning_rate": 8.19234194122885e-06,
      "loss": 0.5415,
      "step": 1079
    },
    {
      "epoch": 2.88,
      "learning_rate": 8.014247551202137e-06,
      "loss": 0.5833,
      "step": 1080
    },
    {
      "epoch": 2.88,
      "learning_rate": 7.836153161175422e-06,
      "loss": 0.6318,
      "step": 1081
    },
    {
      "epoch": 2.89,
      "learning_rate": 7.65805877114871e-06,
      "loss": 0.5398,
      "step": 1082
    },
    {
      "epoch": 2.89,
      "learning_rate": 7.4799643811219954e-06,
      "loss": 0.8625,
      "step": 1083
    },
    {
      "epoch": 2.89,
      "learning_rate": 7.301869991095281e-06,
      "loss": 0.4004,
      "step": 1084
    },
    {
      "epoch": 2.89,
      "learning_rate": 7.123775601068567e-06,
      "loss": 0.636,
      "step": 1085
    },
    {
      "epoch": 2.9,
      "learning_rate": 6.9456812110418536e-06,
      "loss": 0.5235,
      "step": 1086
    },
    {
      "epoch": 2.9,
      "learning_rate": 6.767586821015139e-06,
      "loss": 0.4901,
      "step": 1087
    },
    {
      "epoch": 2.9,
      "learning_rate": 6.589492430988424e-06,
      "loss": 0.2543,
      "step": 1088
    },
    {
      "epoch": 2.9,
      "learning_rate": 6.411398040961709e-06,
      "loss": 0.4768,
      "step": 1089
    },
    {
      "epoch": 2.91,
      "learning_rate": 6.233303650934995e-06,
      "loss": 0.2038,
      "step": 1090
    },
    {
      "epoch": 2.91,
      "learning_rate": 6.055209260908281e-06,
      "loss": 0.3125,
      "step": 1091
    },
    {
      "epoch": 2.91,
      "learning_rate": 5.877114870881568e-06,
      "loss": 0.4375,
      "step": 1092
    },
    {
      "epoch": 2.91,
      "eval_loss": 0.7176805138587952,
      "eval_runtime": 3073.495,
      "eval_samples_per_second": 0.976,
      "eval_steps_per_second": 0.061,
      "step": 1092
    }
  ],
  "logging_steps": 1,
  "max_steps": 1125,
  "num_train_epochs": 3,
  "save_steps": 156,
  "total_flos": 9.257195873540506e+17,
  "trial_name": null,
  "trial_params": null
}