{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9974450689831375,
  "eval_steps": 500,
  "global_step": 244,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 2.0754,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.1342,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 2.1035,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.09,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.5e-05,
      "loss": 2.0643,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.124,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010499999999999999,
      "loss": 2.1867,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.175,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000135,
      "loss": 2.0837,
      "step": 9
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00015,
      "loss": 2.0431,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00014999838015426563,
      "loss": 2.0665,
      "step": 11
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00014999352068703324,
      "loss": 2.0668,
      "step": 12
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001499854218082118,
      "loss": 2.1312,
      "step": 13
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00014997408386763957,
      "loss": 2.0758,
      "step": 14
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00014995950735506895,
      "loss": 2.1173,
      "step": 15
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014994169290014528,
      "loss": 2.0044,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014992064127237976,
      "loss": 2.0054,
      "step": 17
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014989635338111612,
      "loss": 2.0509,
      "step": 18
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001498688302754913,
      "loss": 2.1071,
      "step": 19
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001498380731443903,
      "loss": 1.9549,
      "step": 20
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00014980408331639463,
      "loss": 1.895,
      "step": 21
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000149766862259725,
      "loss": 1.9979,
      "step": 22
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000149726411582178,
      "loss": 2.0151,
      "step": 23
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00014968273303105645,
      "loss": 1.9236,
      "step": 24
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001496358284930941,
      "loss": 1.9613,
      "step": 25
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014958569999437403,
      "loss": 1.9975,
      "step": 26
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014953234970024114,
      "loss": 1.9804,
      "step": 27
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014947577991520874,
      "loss": 1.9211,
      "step": 28
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00014941599308285872,
      "loss": 2.0278,
      "step": 29
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001493529917857364,
      "loss": 1.9682,
      "step": 30
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001492867787452386,
      "loss": 1.8728,
      "step": 31
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00014921735682149628,
      "loss": 2.0241,
      "step": 32
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00014914472901325095,
      "loss": 1.9737,
      "step": 33
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00014906889845772516,
      "loss": 1.9329,
      "step": 34
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00014898986843048698,
      "loss": 1.9861,
      "step": 35
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00014890764234530847,
      "loss": 1.8872,
      "step": 36
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00014882222375401822,
      "loss": 1.9282,
      "step": 37
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00014873361634634805,
      "loss": 2.0487,
      "step": 38
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00014864182394977337,
      "loss": 1.9907,
      "step": 39
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001485468505293482,
      "loss": 2.0665,
      "step": 40
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00014844870018753355,
      "loss": 2.0757,
      "step": 41
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00014834737716402043,
      "loss": 1.9599,
      "step": 42
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001482428858355466,
      "loss": 1.9655,
      "step": 43
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001481352307157077,
      "loss": 1.9234,
      "step": 44
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00014802441645476192,
      "loss": 2.0089,
      "step": 45
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00014791044783942956,
      "loss": 1.94,
      "step": 46
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001477933297926859,
      "loss": 1.9925,
      "step": 47
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00014767306737354885,
      "loss": 1.9783,
      "step": 48
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00014754966577686007,
      "loss": 1.97,
      "step": 49
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000147423130333061,
      "loss": 1.9398,
      "step": 50
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00014729346650796223,
      "loss": 1.963,
      "step": 51
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00014716067990250758,
      "loss": 1.9428,
      "step": 52
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001470247762525322,
      "loss": 1.8047,
      "step": 53
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00014688576142851467,
      "loss": 1.9507,
      "step": 54
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00014674364143532352,
      "loss": 1.9653,
      "step": 55
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001465984224119578,
      "loss": 1.9433,
      "step": 56
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00014645011063128192,
      "loss": 1.9655,
      "step": 57
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001462987124997547,
      "loss": 2.0388,
      "step": 58
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00014614423455715263,
      "loss": 1.8811,
      "step": 59
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00014598668347628733,
      "loss": 1.956,
      "step": 60
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00014582606606271736,
      "loss": 1.9236,
      "step": 61
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001456623892544542,
      "loss": 1.9662,
      "step": 62
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00014549566012166275,
      "loss": 1.9648,
      "step": 63
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00014532588586635558,
      "loss": 1.913,
      "step": 64
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014515307382208215,
      "loss": 2.0282,
      "step": 65
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014497723145361183,
      "loss": 2.0331,
      "step": 66
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001447983663566116,
      "loss": 2.1089,
      "step": 67
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014461648625731783,
      "loss": 2.0694,
      "step": 68
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014443159901220262,
      "loss": 1.9098,
      "step": 69
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001442437126076343,
      "loss": 1.8582,
      "step": 70
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014405283515953277,
      "loss": 1.8942,
      "step": 71
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014385897491301844,
      "loss": 1.9396,
      "step": 72
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00014366214024205654,
      "loss": 1.9624,
      "step": 73
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00014346233964909508,
      "loss": 1.9123,
      "step": 74
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00014325958176469777,
      "loss": 1.9146,
      "step": 75
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001430538753471711,
      "loss": 1.9646,
      "step": 76
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00014284522928218612,
      "loss": 1.8241,
      "step": 77
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001426336525823945,
      "loss": 1.968,
      "step": 78
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00014241915438703928,
      "loss": 1.8584,
      "step": 79
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00014220174396156014,
      "loss": 1.9979,
      "step": 80
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00014198143069719306,
      "loss": 1.9972,
      "step": 81
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00014175822411056476,
      "loss": 1.8241,
      "step": 82
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00014153213384328158,
      "loss": 1.9249,
      "step": 83
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00014130316966151296,
      "loss": 2.076,
      "step": 84
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014107134145556968,
      "loss": 1.9242,
      "step": 85
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014083665923947652,
      "loss": 1.9075,
      "step": 86
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001405991331505398,
      "loss": 1.9701,
      "step": 87
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014035877344890945,
      "loss": 1.9521,
      "step": 88
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001401155905171358,
      "loss": 1.9354,
      "step": 89
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00013986959485972112,
      "loss": 2.0025,
      "step": 90
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001396207971026658,
      "loss": 1.9459,
      "step": 91
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001393692079930095,
      "loss": 1.9798,
      "step": 92
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00013911483839836676,
      "loss": 1.8871,
      "step": 93
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00013885769930645767,
      "loss": 1.9457,
      "step": 94
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001385978018246332,
      "loss": 1.9094,
      "step": 95
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013833515717939538,
      "loss": 1.9651,
      "step": 96
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013806977671591245,
      "loss": 2.0097,
      "step": 97
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013780167189752872,
      "loss": 1.9944,
      "step": 98
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013753085430526945,
      "loss": 1.8378,
      "step": 99
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001372573356373405,
      "loss": 1.9796,
      "step": 100
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013698112770862319,
      "loss": 1.8866,
      "step": 101
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013670224245016375,
      "loss": 2.0077,
      "step": 102
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013642069190865808,
      "loss": 1.8807,
      "step": 103
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00013613648824593137,
      "loss": 2.0118,
      "step": 104
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001358496437384127,
      "loss": 1.9495,
      "step": 105
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001355601707766048,
      "loss": 1.927,
      "step": 106
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001352680818645488,
      "loss": 1.9418,
      "step": 107
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013497338961928406,
      "loss": 1.9557,
      "step": 108
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013467610677030337,
      "loss": 1.9239,
      "step": 109
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001343762461590028,
      "loss": 2.0298,
      "step": 110
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013407382073812724,
      "loss": 1.9778,
      "step": 111
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013376884357121075,
      "loss": 1.8697,
      "step": 112
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013346132783201233,
      "loss": 1.8659,
      "step": 113
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001331512868039469,
      "loss": 1.9608,
      "step": 114
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00013283873387951142,
      "loss": 1.9881,
      "step": 115
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001325236825597065,
      "loss": 1.8963,
      "step": 116
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00013220614645345304,
      "loss": 1.9821,
      "step": 117
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00013188613927700462,
      "loss": 1.8786,
      "step": 118
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00013156367485335483,
      "loss": 1.9391,
      "step": 119
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001312387671116402,
      "loss": 1.8749,
      "step": 120
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00013091143008653864,
      "loss": 1.9711,
      "step": 121
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000130581677917663,
      "loss": 1.9973,
      "step": 122
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00013024952484895047,
      "loss": 1.9736,
      "step": 123
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00012991498522804725,
      "loss": 1.9482,
      "step": 124
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001295780735056887,
      "loss": 1.8969,
      "step": 125
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001292388042350753,
      "loss": 1.8856,
      "step": 126
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00012889719207124386,
      "loss": 1.896,
      "step": 127
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00012855325177043455,
      "loss": 1.9585,
      "step": 128
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00012820699818945344,
      "loss": 2.0194,
      "step": 129
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00012785844628503088,
      "loss": 2.0445,
      "step": 130
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00012750761111317527,
      "loss": 1.9695,
      "step": 131
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00012715450782852281,
      "loss": 1.9849,
      "step": 132
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00012679915168368276,
      "loss": 1.9426,
      "step": 133
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00012644155802857878,
      "loss": 1.8934,
      "step": 134
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00012608174230978572,
      "loss": 1.9616,
      "step": 135
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00012571972006986237,
      "loss": 1.926,
      "step": 136
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00012535550694668034,
      "loss": 1.9333,
      "step": 137
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00012498911867274816,
      "loss": 1.953,
      "step": 138
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001246205710745321,
      "loss": 1.9753,
      "step": 139
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001242498800717723,
      "loss": 1.8901,
      "step": 140
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00012387706167679507,
      "loss": 1.8817,
      "step": 141
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00012350213199382147,
      "loss": 1.939,
      "step": 142
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001231251072182714,
      "loss": 1.9321,
      "step": 143
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00012274600363606418,
      "loss": 2.0088,
      "step": 144
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00012236483762291504,
      "loss": 1.9488,
      "step": 145
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00012198162564362771,
      "loss": 2.0998,
      "step": 146
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00012159638425138327,
      "loss": 1.8385,
      "step": 147
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00012120913008702508,
      "loss": 1.9502,
      "step": 148
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00012081987987833996,
      "loss": 1.9521,
      "step": 149
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00012042865043933565,
      "loss": 2.01,
      "step": 150
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00012003545866951448,
      "loss": 1.945,
      "step": 151
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00011964032155314345,
      "loss": 1.9757,
      "step": 152
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00011924325615852046,
      "loss": 1.9674,
      "step": 153
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00011884427963723716,
      "loss": 1.938,
      "step": 154
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00011844340922343792,
      "loss": 2.0233,
      "step": 155
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001180406622330756,
      "loss": 2.0303,
      "step": 156
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00011763605606316337,
      "loss": 1.9139,
      "step": 157
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001172296081910233,
      "loss": 1.8695,
      "step": 158
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00011682133617353145,
      "loss": 1.9399,
      "step": 159
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00011641125764635947,
      "loss": 1.9003,
      "step": 160
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00011599939032321271,
      "loss": 1.9971,
      "step": 161
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00011558575199506527,
      "loss": 2.0124,
      "step": 162
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00011517036052939132,
      "loss": 1.9316,
      "step": 163
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00011475323386939331,
      "loss": 2.0054,
      "step": 164
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00011433439003322706,
      "loss": 1.7991,
      "step": 165
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00011391384711322323,
      "loss": 1.9603,
      "step": 166
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00011349162327510597,
      "loss": 1.8788,
      "step": 167
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00011306773675720816,
      "loss": 1.8611,
      "step": 168
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00011264220586968362,
      "loss": 2.0317,
      "step": 169
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00011221504899371616,
      "loss": 1.8378,
      "step": 170
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00011178628458072557,
      "loss": 1.9995,
      "step": 171
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00011135593115157072,
      "loss": 1.8996,
      "step": 172
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00011092400729574934,
      "loss": 1.8958,
      "step": 173
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00011049053167059518,
      "loss": 2.0009,
      "step": 174
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00011005552300047206,
      "loss": 1.9154,
      "step": 175
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00010961900007596499,
      "loss": 1.9606,
      "step": 176
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00010918098175306857,
      "loss": 1.8051,
      "step": 177
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00010874148695237245,
      "loss": 1.9606,
      "step": 178
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00010830053465824405,
      "loss": 2.0241,
      "step": 179
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001078581439180085,
      "loss": 1.8999,
      "step": 180
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001074143338411259,
      "loss": 1.8892,
      "step": 181
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00010696912359836585,
      "loss": 1.9695,
      "step": 182
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00010652253242097937,
      "loss": 1.9828,
      "step": 183
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00010607457959986809,
      "loss": 1.899,
      "step": 184
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001056252844847512,
      "loss": 2.0682,
      "step": 185
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00010517466648332935,
      "loss": 1.8665,
      "step": 186
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00010472274506044646,
      "loss": 1.9554,
      "step": 187
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00010426953973724894,
      "loss": 2.0293,
      "step": 188
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00010381507009034231,
      "loss": 1.9689,
      "step": 189
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00010335935575094584,
      "loss": 1.9393,
      "step": 190
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001029024164040442,
      "loss": 1.8898,
      "step": 191
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00010244427178753751,
      "loss": 1.9101,
      "step": 192
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00010198494169138847,
      "loss": 2.0164,
      "step": 193
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001015244459567677,
      "loss": 1.8392,
      "step": 194
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00010106280447519656,
      "loss": 1.9871,
      "step": 195
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00010060003718768793,
      "loss": 1.9528,
      "step": 196
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000100136164083885,
      "loss": 2.0022,
      "step": 197
    },
    {
      "epoch": 0.81,
      "learning_rate": 9.967120520119751e-05,
      "loss": 2.0728,
      "step": 198
    },
    {
      "epoch": 0.81,
      "learning_rate": 9.920518062393657e-05,
      "loss": 1.9121,
      "step": 199
    },
    {
      "epoch": 0.82,
      "learning_rate": 9.873811048244671e-05,
      "loss": 1.8309,
      "step": 200
    },
    {
      "epoch": 0.82,
      "learning_rate": 9.82700149522367e-05,
      "loss": 1.8731,
      "step": 201
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.780091425310777e-05,
      "loss": 1.9089,
      "step": 202
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.733082864828036e-05,
      "loss": 1.8871,
      "step": 203
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.685977844351884e-05,
      "loss": 1.932,
      "step": 204
    },
    {
      "epoch": 0.84,
      "learning_rate": 9.638778398625421e-05,
      "loss": 1.8818,
      "step": 205
    },
    {
      "epoch": 0.84,
      "learning_rate": 9.59148656647054e-05,
      "loss": 2.0086,
      "step": 206
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.54410439069984e-05,
      "loss": 1.9073,
      "step": 207
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.496633918028397e-05,
      "loss": 1.868,
      "step": 208
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.44907719898535e-05,
      "loss": 1.9662,
      "step": 209
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.401436287825326e-05,
      "loss": 1.8944,
      "step": 210
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.3537132424397e-05,
      "loss": 1.9545,
      "step": 211
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.305910124267716e-05,
      "loss": 2.0606,
      "step": 212
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.258028998207425e-05,
      "loss": 1.9157,
      "step": 213
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.210071932526506e-05,
      "loss": 1.965,
      "step": 214
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.162040998772913e-05,
      "loss": 1.9563,
      "step": 215
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.113938271685392e-05,
      "loss": 1.8179,
      "step": 216
    },
    {
      "epoch": 0.89,
      "learning_rate": 9.065765829103874e-05,
      "loss": 1.9514,
      "step": 217
    },
    {
      "epoch": 0.89,
      "learning_rate": 9.01752575187971e-05,
      "loss": 1.9616,
      "step": 218
    },
    {
      "epoch": 0.9,
      "learning_rate": 8.969220123785786e-05,
      "loss": 1.9105,
      "step": 219
    },
    {
      "epoch": 0.9,
      "learning_rate": 8.920851031426521e-05,
      "loss": 1.9349,
      "step": 220
    },
    {
      "epoch": 0.9,
      "learning_rate": 8.872420564147722e-05,
      "loss": 1.902,
      "step": 221
    },
    {
      "epoch": 0.91,
      "learning_rate": 8.823930813946351e-05,
      "loss": 2.0122,
      "step": 222
    },
    {
      "epoch": 0.91,
      "learning_rate": 8.775383875380138e-05,
      "loss": 1.9486,
      "step": 223
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.72678184547712e-05,
      "loss": 1.9728,
      "step": 224
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.678126823645052e-05,
      "loss": 1.919,
      "step": 225
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.62942091158072e-05,
      "loss": 1.8079,
      "step": 226
    },
    {
      "epoch": 0.93,
      "learning_rate": 8.580666213179165e-05,
      "loss": 1.9733,
      "step": 227
    },
    {
      "epoch": 0.93,
      "learning_rate": 8.531864834442792e-05,
      "loss": 1.9641,
      "step": 228
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.483018883390405e-05,
      "loss": 2.0346,
      "step": 229
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.434130469966152e-05,
      "loss": 1.919,
      "step": 230
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.385201705948375e-05,
      "loss": 1.9831,
      "step": 231
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.336234704858398e-05,
      "loss": 2.0287,
      "step": 232
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.287231581869235e-05,
      "loss": 2.0557,
      "step": 233
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.238194453714209e-05,
      "loss": 1.8527,
      "step": 234
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.189125438595531e-05,
      "loss": 1.8578,
      "step": 235
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.140026656092794e-05,
      "loss": 1.9493,
      "step": 236
    },
    {
      "epoch": 0.97,
      "learning_rate": 8.090900227071425e-05,
      "loss": 1.9758,
      "step": 237
    },
    {
      "epoch": 0.97,
      "learning_rate": 8.04174827359106e-05,
      "loss": 2.0026,
      "step": 238
    },
    {
      "epoch": 0.98,
      "learning_rate": 7.992572918813897e-05,
      "loss": 1.9079,
      "step": 239
    },
    {
      "epoch": 0.98,
      "learning_rate": 7.943376286912961e-05,
      "loss": 2.0169,
      "step": 240
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.894160502980368e-05,
      "loss": 1.937,
      "step": 241
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.844927692935528e-05,
      "loss": 1.912,
      "step": 242
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.795679983433301e-05,
      "loss": 1.9314,
      "step": 243
    },
    {
      "epoch": 1.0,
      "learning_rate": 7.74641950177214e-05,
      "loss": 1.8367,
      "step": 244
    }
  ],
  "logging_steps": 1,
  "max_steps": 488,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 244,
  "total_flos": 3.2149768164228465e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}