{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 310,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 11.2153,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 11.2101,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 11.1907,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 11.0346,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 10.6171,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012,
      "loss": 10.0148,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014,
      "loss": 9.4405,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016,
      "loss": 9.7438,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018,
      "loss": 8.707,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 8.8771,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019999451693655123,
      "loss": 8.7858,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019997806834748456,
      "loss": 8.511,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019995065603657316,
      "loss": 8.2111,
      "step": 13
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019991228300988585,
      "loss": 8.0204,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001998629534754574,
      "loss": 7.9454,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019980267284282717,
      "loss": 7.8055,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019973144772244582,
      "loss": 7.6032,
      "step": 17
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019964928592495045,
      "loss": 7.7403,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019955619646030802,
      "loss": 7.7085,
      "step": 19
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019945218953682734,
      "loss": 7.5279,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019933727656003963,
      "loss": 7.2119,
      "step": 21
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001992114701314478,
      "loss": 6.9685,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019907478404714436,
      "loss": 6.8322,
      "step": 23
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019892723329629887,
      "loss": 6.7232,
      "step": 24
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019876883405951377,
      "loss": 6.7616,
      "step": 25
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001985996037070505,
      "loss": 6.5955,
      "step": 26
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001984195607969242,
      "loss": 6.4523,
      "step": 27
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001982287250728689,
      "loss": 6.3178,
      "step": 28
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019802711746217218,
      "loss": 6.371,
      "step": 29
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019781476007338058,
      "loss": 6.4004,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019759167619387476,
      "loss": 6.2502,
      "step": 31
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019735789028731604,
      "loss": 6.1807,
      "step": 32
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019711342799096361,
      "loss": 6.1244,
      "step": 33
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001968583161128631,
      "loss": 6.0723,
      "step": 34
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019659258262890683,
      "loss": 5.8887,
      "step": 35
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019631625667976583,
      "loss": 5.8987,
      "step": 36
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001960293685676943,
      "loss": 5.5855,
      "step": 37
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019573194975320673,
      "loss": 5.7129,
      "step": 38
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001954240328516277,
      "loss": 5.8263,
      "step": 39
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019510565162951537,
      "loss": 5.7092,
      "step": 40
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001947768410009586,
      "loss": 5.6344,
      "step": 41
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019443763702374812,
      "loss": 5.5662,
      "step": 42
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019408807689542257,
      "loss": 5.5991,
      "step": 43
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019372819894918915,
      "loss": 5.3797,
      "step": 44
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019335804264972018,
      "loss": 5.4445,
      "step": 45
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019297764858882514,
      "loss": 5.4585,
      "step": 46
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001925870584809995,
      "loss": 5.2898,
      "step": 47
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019218631515885006,
      "loss": 5.196,
      "step": 48
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019177546256839812,
      "loss": 5.2029,
      "step": 49
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001913545457642601,
      "loss": 5.3546,
      "step": 50
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019092361090470688,
      "loss": 5.2278,
      "step": 51
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019048270524660196,
      "loss": 5.2661,
      "step": 52
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019003187714021938,
      "loss": 5.0926,
      "step": 53
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001895711760239413,
      "loss": 5.2142,
      "step": 54
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001891006524188368,
      "loss": 5.1078,
      "step": 55
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018862035792312147,
      "loss": 5.1481,
      "step": 56
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001881303452064992,
      "loss": 5.1971,
      "step": 57
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018763066800438636,
      "loss": 5.1135,
      "step": 58
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018712138111201895,
      "loss": 5.1675,
      "step": 59
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018660254037844388,
      "loss": 4.9891,
      "step": 60
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001860742027003944,
      "loss": 4.9451,
      "step": 61
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018553642601605068,
      "loss": 4.8872,
      "step": 62
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018498926929868642,
      "loss": 5.0473,
      "step": 63
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018443279255020152,
      "loss": 4.9591,
      "step": 64
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018386705679454242,
      "loss": 4.8218,
      "step": 65
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018329212407100994,
      "loss": 4.8672,
      "step": 66
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018270805742745617,
      "loss": 4.9517,
      "step": 67
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018211492091337042,
      "loss": 4.7033,
      "step": 68
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018151277957285543,
      "loss": 4.6816,
      "step": 69
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018090169943749476,
      "loss": 4.6706,
      "step": 70
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018028174751911146,
      "loss": 4.8965,
      "step": 71
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017965299180241963,
      "loss": 4.5277,
      "step": 72
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017901550123756906,
      "loss": 4.709,
      "step": 73
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000178369345732584,
      "loss": 4.5827,
      "step": 74
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001777145961456971,
      "loss": 4.526,
      "step": 75
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017705132427757895,
      "loss": 4.4775,
      "step": 76
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017637960286346425,
      "loss": 4.389,
      "step": 77
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017569950556517566,
      "loss": 4.5912,
      "step": 78
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017501110696304596,
      "loss": 4.3966,
      "step": 79
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017431448254773944,
      "loss": 4.3832,
      "step": 80
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017360970871197346,
      "loss": 4.3049,
      "step": 81
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017289686274214118,
      "loss": 4.5175,
      "step": 82
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017217602280983623,
      "loss": 4.4391,
      "step": 83
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017144726796328034,
      "loss": 4.359,
      "step": 84
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017071067811865476,
      "loss": 4.4578,
      "step": 85
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016996633405133655,
      "loss": 4.2509,
      "step": 86
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001692143173870407,
      "loss": 4.213,
      "step": 87
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016845471059286887,
      "loss": 4.3808,
      "step": 88
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016768759696826608,
      "loss": 4.2431,
      "step": 89
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016691306063588583,
      "loss": 4.1752,
      "step": 90
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016613118653236518,
      "loss": 4.1288,
      "step": 91
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016534206039901057,
      "loss": 4.2743,
      "step": 92
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016454576877239507,
      "loss": 4.1326,
      "step": 93
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000163742398974869,
      "loss": 4.2462,
      "step": 94
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016293203910498376,
      "loss": 4.1801,
      "step": 95
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016211477802783103,
      "loss": 4.2519,
      "step": 96
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016129070536529766,
      "loss": 4.1227,
      "step": 97
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001604599114862375,
      "loss": 4.096,
      "step": 98
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001596224874965616,
      "loss": 4.1539,
      "step": 99
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015877852522924732,
      "loss": 4.1399,
      "step": 100
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001579281172342679,
      "loss": 4.0179,
      "step": 101
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001570713567684432,
      "loss": 4.2023,
      "step": 102
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015620833778521307,
      "loss": 4.017,
      "step": 103
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015533915492433443,
      "loss": 4.0196,
      "step": 104
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015446390350150273,
      "loss": 4.0342,
      "step": 105
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015358267949789966,
      "loss": 4.2113,
      "step": 106
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015269557954966778,
      "loss": 3.9744,
      "step": 107
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015180270093731303,
      "loss": 3.9296,
      "step": 108
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015090414157503714,
      "loss": 4.1932,
      "step": 109
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.9307,
      "step": 110
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014909037536151409,
      "loss": 4.1181,
      "step": 111
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014817536741017152,
      "loss": 4.0439,
      "step": 112
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014725507648690543,
      "loss": 4.0253,
      "step": 113
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014632960351198618,
      "loss": 4.0668,
      "step": 114
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014539904997395468,
      "loss": 3.9828,
      "step": 115
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014446351791849276,
      "loss": 4.0319,
      "step": 116
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014352310993723277,
      "loss": 3.9696,
      "step": 117
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014257792915650728,
      "loss": 3.9411,
      "step": 118
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014162807922604012,
      "loss": 4.0313,
      "step": 119
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014067366430758004,
      "loss": 3.9115,
      "step": 120
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013971478906347806,
      "loss": 3.941,
      "step": 121
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001387515586452103,
      "loss": 3.975,
      "step": 122
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013778407868184672,
      "loss": 3.7062,
      "step": 123
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013681245526846783,
      "loss": 3.8805,
      "step": 124
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013583679495453,
      "loss": 3.7612,
      "step": 125
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013485720473218154,
      "loss": 3.7326,
      "step": 126
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013387379202452917,
      "loss": 3.8042,
      "step": 127
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013288666467385833,
      "loss": 3.9848,
      "step": 128
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013189593092980702,
      "loss": 4.011,
      "step": 129
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.8322,
      "step": 130
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012990407922560868,
      "loss": 3.7704,
      "step": 131
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012890317969444716,
      "loss": 3.8909,
      "step": 132
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012789911060392294,
      "loss": 3.8207,
      "step": 133
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012689198206152657,
      "loss": 3.8095,
      "step": 134
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012588190451025207,
      "loss": 3.8504,
      "step": 135
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001248689887164855,
      "loss": 3.6548,
      "step": 136
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001238533457578581,
      "loss": 3.7723,
      "step": 137
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012283508701106557,
      "loss": 3.6582,
      "step": 138
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012181432413965428,
      "loss": 3.6674,
      "step": 139
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012079116908177593,
      "loss": 3.9033,
      "step": 140
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011976573403791262,
      "loss": 3.7011,
      "step": 141
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011873813145857249,
      "loss": 3.8179,
      "step": 142
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011770847403195834,
      "loss": 3.6867,
      "step": 143
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011667687467161024,
      "loss": 3.6831,
      "step": 144
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001156434465040231,
      "loss": 3.8595,
      "step": 145
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011460830285624118,
      "loss": 3.721,
      "step": 146
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011357155724343045,
      "loss": 3.712,
      "step": 147
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011253332335643043,
      "loss": 3.6603,
      "step": 148
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011149371504928668,
      "loss": 3.6563,
      "step": 149
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011045284632676536,
      "loss": 3.5381,
      "step": 150
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010941083133185146,
      "loss": 3.7151,
      "step": 151
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010836778433323158,
      "loss": 3.7003,
      "step": 152
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010732381971276318,
      "loss": 3.8455,
      "step": 153
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010627905195293135,
      "loss": 3.5937,
      "step": 154
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001052335956242944,
      "loss": 3.5345,
      "step": 155
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010418756537291996,
      "loss": 3.527,
      "step": 156
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010314107590781284,
      "loss": 3.5617,
      "step": 157
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001020942419883357,
      "loss": 3.5834,
      "step": 158
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010104717841162458,
      "loss": 3.6394,
      "step": 159
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 3.4265,
      "step": 160
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.895282158837545e-05,
      "loss": 3.4816,
      "step": 161
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.790575801166432e-05,
      "loss": 3.5481,
      "step": 162
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.685892409218717e-05,
      "loss": 3.6996,
      "step": 163
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.581243462708006e-05,
      "loss": 3.6275,
      "step": 164
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.476640437570562e-05,
      "loss": 3.5595,
      "step": 165
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.372094804706867e-05,
      "loss": 3.4173,
      "step": 166
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.267618028723686e-05,
      "loss": 3.6742,
      "step": 167
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.163221566676847e-05,
      "loss": 3.5923,
      "step": 168
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.058916866814858e-05,
      "loss": 3.5414,
      "step": 169
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.954715367323468e-05,
      "loss": 3.7635,
      "step": 170
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.850628495071336e-05,
      "loss": 3.3945,
      "step": 171
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.746667664356956e-05,
      "loss": 3.5575,
      "step": 172
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.642844275656957e-05,
      "loss": 3.4334,
      "step": 173
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.539169714375885e-05,
      "loss": 3.5686,
      "step": 174
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.7207,
      "step": 175
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.332312532838978e-05,
      "loss": 3.4545,
      "step": 176
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.229152596804168e-05,
      "loss": 3.4879,
      "step": 177
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.126186854142752e-05,
      "loss": 3.6279,
      "step": 178
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.023426596208739e-05,
      "loss": 3.4412,
      "step": 179
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.920883091822408e-05,
      "loss": 3.5066,
      "step": 180
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.818567586034577e-05,
      "loss": 3.3587,
      "step": 181
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.716491298893442e-05,
      "loss": 3.5664,
      "step": 182
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.614665424214193e-05,
      "loss": 3.4065,
      "step": 183
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.513101128351454e-05,
      "loss": 3.6623,
      "step": 184
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.411809548974792e-05,
      "loss": 3.3463,
      "step": 185
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.310801793847344e-05,
      "loss": 3.5487,
      "step": 186
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.210088939607708e-05,
      "loss": 3.3901,
      "step": 187
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.109682030555283e-05,
      "loss": 3.2565,
      "step": 188
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.009592077439134e-05,
      "loss": 3.4692,
      "step": 189
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.909830056250527e-05,
      "loss": 3.4258,
      "step": 190
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.8104069070193e-05,
      "loss": 3.4803,
      "step": 191
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.711333532614168e-05,
      "loss": 3.5306,
      "step": 192
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.612620797547087e-05,
      "loss": 3.4718,
      "step": 193
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.51427952678185e-05,
      "loss": 3.4513,
      "step": 194
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.416320504546997e-05,
      "loss": 3.6049,
      "step": 195
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.318754473153221e-05,
      "loss": 3.4402,
      "step": 196
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.22159213181533e-05,
      "loss": 3.4833,
      "step": 197
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.12484413547897e-05,
      "loss": 3.493,
      "step": 198
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.0285210936521955e-05,
      "loss": 3.3789,
      "step": 199
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 3.386,
      "step": 200
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.83719207739599e-05,
      "loss": 3.5344,
      "step": 201
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 3.4203,
      "step": 202
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.647689006276726e-05,
      "loss": 3.5331,
      "step": 203
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.553648208150728e-05,
      "loss": 3.5052,
      "step": 204
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 3.631,
      "step": 205
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.3670396488013854e-05,
      "loss": 3.4552,
      "step": 206
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.274492351309461e-05,
      "loss": 3.4078,
      "step": 207
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.182463258982846e-05,
      "loss": 3.4163,
      "step": 208
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.090962463848592e-05,
      "loss": 3.4208,
      "step": 209
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.5513,
      "step": 210
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.909585842496287e-05,
      "loss": 3.4736,
      "step": 211
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.8197299062686995e-05,
      "loss": 3.4162,
      "step": 212
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.7304420450332244e-05,
      "loss": 3.4161,
      "step": 213
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.6417320502100316e-05,
      "loss": 3.5424,
      "step": 214
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.5536096498497295e-05,
      "loss": 3.4375,
      "step": 215
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.46608450756656e-05,
      "loss": 3.4181,
      "step": 216
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.379166221478697e-05,
      "loss": 3.4234,
      "step": 217
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.2928643231556844e-05,
      "loss": 3.2769,
      "step": 218
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.207188276573214e-05,
      "loss": 3.5804,
      "step": 219
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.4969,
      "step": 220
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.037751250343841e-05,
      "loss": 3.4878,
      "step": 221
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.954008851376252e-05,
      "loss": 3.4461,
      "step": 222
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.8709294634702376e-05,
      "loss": 3.4997,
      "step": 223
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.788522197216897e-05,
      "loss": 3.2672,
      "step": 224
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.7067960895016275e-05,
      "loss": 3.4284,
      "step": 225
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.6257601025131026e-05,
      "loss": 3.3721,
      "step": 226
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.545423122760493e-05,
      "loss": 3.3755,
      "step": 227
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.465793960098945e-05,
      "loss": 3.412,
      "step": 228
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.386881346763483e-05,
      "loss": 3.3902,
      "step": 229
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.308693936411421e-05,
      "loss": 3.3975,
      "step": 230
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.231240303173394e-05,
      "loss": 3.3772,
      "step": 231
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.154528940713113e-05,
      "loss": 3.1924,
      "step": 232
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.078568261295933e-05,
      "loss": 3.439,
      "step": 233
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0033665948663448e-05,
      "loss": 3.2018,
      "step": 234
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 3.4706,
      "step": 235
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8552732036719687e-05,
      "loss": 3.4761,
      "step": 236
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.7823977190163786e-05,
      "loss": 3.4259,
      "step": 237
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 3.4053,
      "step": 238
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.639029128802657e-05,
      "loss": 3.2636,
      "step": 239
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 3.3724,
      "step": 240
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4988893036954043e-05,
      "loss": 3.3544,
      "step": 241
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4300494434824373e-05,
      "loss": 3.2656,
      "step": 242
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.362039713653581e-05,
      "loss": 3.4023,
      "step": 243
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2948675722421086e-05,
      "loss": 3.2969,
      "step": 244
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2285403854302912e-05,
      "loss": 3.4511,
      "step": 245
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.163065426741603e-05,
      "loss": 3.4428,
      "step": 246
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.098449876243096e-05,
      "loss": 3.3647,
      "step": 247
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0347008197580374e-05,
      "loss": 3.2604,
      "step": 248
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9718252480888566e-05,
      "loss": 3.3492,
      "step": 249
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 3.3132,
      "step": 250
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.848722042714457e-05,
      "loss": 3.1101,
      "step": 251
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.78850790866296e-05,
      "loss": 3.4295,
      "step": 252
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7291942572543807e-05,
      "loss": 3.27,
      "step": 253
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6707875928990058e-05,
      "loss": 3.307,
      "step": 254
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6132943205457606e-05,
      "loss": 3.2597,
      "step": 255
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5567207449798515e-05,
      "loss": 3.2053,
      "step": 256
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5010730701313625e-05,
      "loss": 3.2863,
      "step": 257
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4463573983949341e-05,
      "loss": 3.1945,
      "step": 258
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3925797299605647e-05,
      "loss": 3.3066,
      "step": 259
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.339745962155613e-05,
      "loss": 3.3855,
      "step": 260
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2878618887981064e-05,
      "loss": 3.1933,
      "step": 261
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2369331995613665e-05,
      "loss": 3.4084,
      "step": 262
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1869654793500784e-05,
      "loss": 3.315,
      "step": 263
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1379642076878527e-05,
      "loss": 3.3994,
      "step": 264
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.2624,
      "step": 265
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.042882397605871e-05,
      "loss": 3.2287,
      "step": 266
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.968122859780648e-06,
      "loss": 3.245,
      "step": 267
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.517294753398064e-06,
      "loss": 3.2106,
      "step": 268
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.076389095293148e-06,
      "loss": 3.2575,
      "step": 269
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.645454235739903e-06,
      "loss": 3.3462,
      "step": 270
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.224537431601886e-06,
      "loss": 3.5159,
      "step": 271
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.81368484114996e-06,
      "loss": 3.3177,
      "step": 272
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.412941519000527e-06,
      "loss": 3.1598,
      "step": 273
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.022351411174866e-06,
      "loss": 3.4421,
      "step": 274
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.6419573502798374e-06,
      "loss": 3.2242,
      "step": 275
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.2718010508108545e-06,
      "loss": 3.3379,
      "step": 276
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.911923104577455e-06,
      "loss": 3.3409,
      "step": 277
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.562362976251901e-06,
      "loss": 3.2563,
      "step": 278
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.223158999041444e-06,
      "loss": 3.322,
      "step": 279
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 3.365,
      "step": 280
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.575967148372317e-06,
      "loss": 3.3066,
      "step": 281
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.268050246793276e-06,
      "loss": 3.2917,
      "step": 282
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.970631432305694e-06,
      "loss": 3.2967,
      "step": 283
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.68374332023419e-06,
      "loss": 3.2636,
      "step": 284
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.40741737109318e-06,
      "loss": 3.2059,
      "step": 285
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.1416838871368924e-06,
      "loss": 3.2664,
      "step": 286
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8865720090364034e-06,
      "loss": 3.4219,
      "step": 287
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.6421097126839712e-06,
      "loss": 3.3064,
      "step": 288
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.4083238061252567e-06,
      "loss": 3.1889,
      "step": 289
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 3.4085,
      "step": 290
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9728825378278246e-06,
      "loss": 3.3206,
      "step": 291
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.771274927131139e-06,
      "loss": 3.4628,
      "step": 292
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.580439203075812e-06,
      "loss": 3.1341,
      "step": 293
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.400396292949513e-06,
      "loss": 3.3387,
      "step": 294
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.231165940486234e-06,
      "loss": 3.2056,
      "step": 295
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0727667037011668e-06,
      "loss": 3.1854,
      "step": 296
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.252159528556403e-07,
      "loss": 3.2785,
      "step": 297
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.885298685522235e-07,
      "loss": 3.4136,
      "step": 298
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.627234399603555e-07,
      "loss": 3.2466,
      "step": 299
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.478104631726711e-07,
      "loss": 3.5445,
      "step": 300
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.438035396920004e-07,
      "loss": 3.4556,
      "step": 301
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.50714075049563e-07,
      "loss": 3.0958,
      "step": 302
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.685522775541904e-07,
      "loss": 3.3386,
      "step": 303
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.973271571728441e-07,
      "loss": 3.3139,
      "step": 304
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3704652454261668e-07,
      "loss": 3.2791,
      "step": 305
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.771699011416168e-08,
      "loss": 3.2188,
      "step": 306
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.934396342684e-08,
      "loss": 3.3562,
      "step": 307
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.193165251545004e-08,
      "loss": 3.3555,
      "step": 308
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.483063448785686e-09,
      "loss": 3.609,
      "step": 309
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 3.4165,
      "step": 310
    },
    {
      "epoch": 1.0,
      "step": 310,
      "total_flos": 53958111068160.0,
      "train_loss": 4.296783600314971,
      "train_runtime": 4111.9826,
      "train_samples_per_second": 7.229,
      "train_steps_per_second": 0.075
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 310,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 53958111068160.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}