{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 108,
  "global_step": 216,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004629629629629629,
      "grad_norm": 0.4398077726364136,
      "learning_rate": 2e-05,
      "loss": 1.1885,
      "step": 1
    },
    {
      "epoch": 0.004629629629629629,
      "eval_loss": 1.181751012802124,
      "eval_runtime": 16.5418,
      "eval_samples_per_second": 22.005,
      "eval_steps_per_second": 2.781,
      "step": 1
    },
    {
      "epoch": 0.009259259259259259,
      "grad_norm": 0.4034997820854187,
      "learning_rate": 4e-05,
      "loss": 1.294,
      "step": 2
    },
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 0.3441363573074341,
      "learning_rate": 6e-05,
      "loss": 1.1688,
      "step": 3
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 0.3627238869667053,
      "learning_rate": 8e-05,
      "loss": 1.1068,
      "step": 4
    },
    {
      "epoch": 0.023148148148148147,
      "grad_norm": 0.4161143898963928,
      "learning_rate": 0.0001,
      "loss": 1.2275,
      "step": 5
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 0.3521893620491028,
      "learning_rate": 0.00012,
      "loss": 1.0201,
      "step": 6
    },
    {
      "epoch": 0.032407407407407406,
      "grad_norm": 0.3282751142978668,
      "learning_rate": 0.00014,
      "loss": 1.0386,
      "step": 7
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.3734138607978821,
      "learning_rate": 0.00016,
      "loss": 1.1113,
      "step": 8
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 0.31210270524024963,
      "learning_rate": 0.00018,
      "loss": 0.8375,
      "step": 9
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 0.3017318844795227,
      "learning_rate": 0.0002,
      "loss": 0.7965,
      "step": 10
    },
    {
      "epoch": 0.05092592592592592,
      "grad_norm": 0.3388109803199768,
      "learning_rate": 0.00019998837141446378,
      "loss": 0.7386,
      "step": 11
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.3247002959251404,
      "learning_rate": 0.00019995348836233516,
      "loss": 0.591,
      "step": 12
    },
    {
      "epoch": 0.06018518518518518,
      "grad_norm": 0.2645561695098877,
      "learning_rate": 0.00019989535895642525,
      "loss": 0.5455,
      "step": 13
    },
    {
      "epoch": 0.06481481481481481,
      "grad_norm": 0.26551955938339233,
      "learning_rate": 0.00019981399671598939,
      "loss": 0.5003,
      "step": 14
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 0.2658671736717224,
      "learning_rate": 0.00019970942056358307,
      "loss": 0.5077,
      "step": 15
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.33185991644859314,
      "learning_rate": 0.00019958165482066094,
      "loss": 0.5111,
      "step": 16
    },
    {
      "epoch": 0.0787037037037037,
      "grad_norm": 0.327854186296463,
      "learning_rate": 0.0001994307292019204,
      "loss": 0.4994,
      "step": 17
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.2778171896934509,
      "learning_rate": 0.0001992566788083908,
      "loss": 0.5184,
      "step": 18
    },
    {
      "epoch": 0.08796296296296297,
      "grad_norm": 0.22942981123924255,
      "learning_rate": 0.00019905954411926992,
      "loss": 0.4833,
      "step": 19
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.18429657816886902,
      "learning_rate": 0.00019883937098250963,
      "loss": 0.4244,
      "step": 20
    },
    {
      "epoch": 0.09722222222222222,
      "grad_norm": 0.20559769868850708,
      "learning_rate": 0.000198596210604153,
      "loss": 0.4432,
      "step": 21
    },
    {
      "epoch": 0.10185185185185185,
      "grad_norm": 0.1754508763551712,
      "learning_rate": 0.00019833011953642525,
      "loss": 0.4271,
      "step": 22
    },
    {
      "epoch": 0.10648148148148148,
      "grad_norm": 0.150568887591362,
      "learning_rate": 0.00019804115966458115,
      "loss": 0.443,
      "step": 23
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.15353460609912872,
      "learning_rate": 0.0001977293981925125,
      "loss": 0.4264,
      "step": 24
    },
    {
      "epoch": 0.11574074074074074,
      "grad_norm": 0.14020614326000214,
      "learning_rate": 0.00019739490762711812,
      "loss": 0.4575,
      "step": 25
    },
    {
      "epoch": 0.12037037037037036,
      "grad_norm": 0.14703242480754852,
      "learning_rate": 0.00019703776576144105,
      "loss": 0.4824,
      "step": 26
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.171169713139534,
      "learning_rate": 0.00019665805565657603,
      "loss": 0.4568,
      "step": 27
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 0.13848260045051575,
      "learning_rate": 0.0001962558656223516,
      "loss": 0.4729,
      "step": 28
    },
    {
      "epoch": 0.13425925925925927,
      "grad_norm": 0.11175956577062607,
      "learning_rate": 0.00019583128919679215,
      "loss": 0.3614,
      "step": 29
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 0.11471609771251678,
      "learning_rate": 0.00019538442512436328,
      "loss": 0.3938,
      "step": 30
    },
    {
      "epoch": 0.14351851851851852,
      "grad_norm": 0.1153385117650032,
      "learning_rate": 0.00019491537733300676,
      "loss": 0.4317,
      "step": 31
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.10725446045398712,
      "learning_rate": 0.00019442425490996988,
      "loss": 0.4493,
      "step": 32
    },
    {
      "epoch": 0.1527777777777778,
      "grad_norm": 0.11065792292356491,
      "learning_rate": 0.0001939111720764347,
      "loss": 0.4004,
      "step": 33
    },
    {
      "epoch": 0.1574074074074074,
      "grad_norm": 0.12286635488271713,
      "learning_rate": 0.00019337624816095358,
      "loss": 0.5065,
      "step": 34
    },
    {
      "epoch": 0.16203703703703703,
      "grad_norm": 0.11002598702907562,
      "learning_rate": 0.0001928196075716966,
      "loss": 0.4308,
      "step": 35
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.09922719746828079,
      "learning_rate": 0.00019224137976751795,
      "loss": 0.344,
      "step": 36
    },
    {
      "epoch": 0.1712962962962963,
      "grad_norm": 0.1075102686882019,
      "learning_rate": 0.00019164169922784716,
      "loss": 0.4705,
      "step": 37
    },
    {
      "epoch": 0.17592592592592593,
      "grad_norm": 0.11824163794517517,
      "learning_rate": 0.00019102070542141328,
      "loss": 0.3725,
      "step": 38
    },
    {
      "epoch": 0.18055555555555555,
      "grad_norm": 0.11450410634279251,
      "learning_rate": 0.0001903785427738082,
      "loss": 0.3854,
      "step": 39
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.13033916056156158,
      "learning_rate": 0.00018971536063389744,
      "loss": 0.4519,
      "step": 40
    },
    {
      "epoch": 0.18981481481481483,
      "grad_norm": 0.12207476049661636,
      "learning_rate": 0.00018903131323908578,
      "loss": 0.3709,
      "step": 41
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 0.10579460859298706,
      "learning_rate": 0.00018832655967944607,
      "loss": 0.3767,
      "step": 42
    },
    {
      "epoch": 0.19907407407407407,
      "grad_norm": 0.12160316854715347,
      "learning_rate": 0.00018760126386071935,
      "loss": 0.4176,
      "step": 43
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 0.11053751409053802,
      "learning_rate": 0.0001868555944661949,
      "loss": 0.4282,
      "step": 44
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 0.11802718043327332,
      "learning_rate": 0.00018608972491747944,
      "loss": 0.3983,
      "step": 45
    },
    {
      "epoch": 0.21296296296296297,
      "grad_norm": 0.1361842304468155,
      "learning_rate": 0.00018530383333416418,
      "loss": 0.4587,
      "step": 46
    },
    {
      "epoch": 0.2175925925925926,
      "grad_norm": 0.1138835921883583,
      "learning_rate": 0.00018449810249239902,
      "loss": 0.4004,
      "step": 47
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.11451338976621628,
      "learning_rate": 0.0001836727197823842,
      "loss": 0.4509,
      "step": 48
    },
    {
      "epoch": 0.22685185185185186,
      "grad_norm": 0.12116890400648117,
      "learning_rate": 0.00018282787716478868,
      "loss": 0.4331,
      "step": 49
    },
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 0.11061301827430725,
      "learning_rate": 0.00018196377112610526,
      "loss": 0.367,
      "step": 50
    },
    {
      "epoch": 0.2361111111111111,
      "grad_norm": 0.13139884173870087,
      "learning_rate": 0.00018108060263295362,
      "loss": 0.4631,
      "step": 51
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 0.1242774948477745,
      "learning_rate": 0.00018017857708534107,
      "loss": 0.3843,
      "step": 52
    },
    {
      "epoch": 0.24537037037037038,
      "grad_norm": 0.12658777832984924,
      "learning_rate": 0.00017925790426889235,
      "loss": 0.3888,
      "step": 53
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.12799492478370667,
      "learning_rate": 0.00017831879830605937,
      "loss": 0.3476,
      "step": 54
    },
    {
      "epoch": 0.25462962962962965,
      "grad_norm": 0.13426098227500916,
      "learning_rate": 0.00017736147760632248,
      "loss": 0.4578,
      "step": 55
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.12698565423488617,
      "learning_rate": 0.0001763861648153945,
      "loss": 0.4511,
      "step": 56
    },
    {
      "epoch": 0.2638888888888889,
      "grad_norm": 0.10626720637083054,
      "learning_rate": 0.00017539308676343973,
      "loss": 0.3417,
      "step": 57
    },
    {
      "epoch": 0.26851851851851855,
      "grad_norm": 0.11828374862670898,
      "learning_rate": 0.0001743824744123196,
      "loss": 0.431,
      "step": 58
    },
    {
      "epoch": 0.27314814814814814,
      "grad_norm": 0.12974177300930023,
      "learning_rate": 0.00017335456280187752,
      "loss": 0.472,
      "step": 59
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.11126148700714111,
      "learning_rate": 0.00017230959099527512,
      "loss": 0.3984,
      "step": 60
    },
    {
      "epoch": 0.2824074074074074,
      "grad_norm": 0.1262761354446411,
      "learning_rate": 0.0001712478020233932,
      "loss": 0.409,
      "step": 61
    },
    {
      "epoch": 0.28703703703703703,
      "grad_norm": 0.12113980203866959,
      "learning_rate": 0.00017016944282830933,
      "loss": 0.4328,
      "step": 62
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 0.12315801531076431,
      "learning_rate": 0.00016907476420586633,
      "loss": 0.389,
      "step": 63
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.1181735098361969,
      "learning_rate": 0.00016796402074734402,
      "loss": 0.4255,
      "step": 64
    },
    {
      "epoch": 0.30092592592592593,
      "grad_norm": 0.12145352363586426,
      "learning_rate": 0.00016683747078024888,
      "loss": 0.3954,
      "step": 65
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 0.11947956681251526,
      "learning_rate": 0.00016569537630823383,
      "loss": 0.3895,
      "step": 66
    },
    {
      "epoch": 0.3101851851851852,
      "grad_norm": 0.12213783711194992,
      "learning_rate": 0.0001645380029501641,
      "loss": 0.4496,
      "step": 67
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 0.11353302001953125,
      "learning_rate": 0.00016336561987834153,
      "loss": 0.4209,
      "step": 68
    },
    {
      "epoch": 0.3194444444444444,
      "grad_norm": 0.10145577788352966,
      "learning_rate": 0.00016217849975590272,
      "loss": 0.375,
      "step": 69
    },
    {
      "epoch": 0.32407407407407407,
      "grad_norm": 0.13219210505485535,
      "learning_rate": 0.00016097691867340545,
      "loss": 0.3499,
      "step": 70
    },
    {
      "epoch": 0.3287037037037037,
      "grad_norm": 0.12123432010412216,
      "learning_rate": 0.00015976115608461758,
      "loss": 0.4793,
      "step": 71
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.11631368845701218,
      "learning_rate": 0.00015853149474152423,
      "loss": 0.4143,
      "step": 72
    },
    {
      "epoch": 0.33796296296296297,
      "grad_norm": 0.13316309452056885,
      "learning_rate": 0.00015728822062856758,
      "loss": 0.4258,
      "step": 73
    },
    {
      "epoch": 0.3425925925925926,
      "grad_norm": 0.1209026649594307,
      "learning_rate": 0.00015603162289613503,
      "loss": 0.4195,
      "step": 74
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 0.1319185197353363,
      "learning_rate": 0.0001547619937933108,
      "loss": 0.3667,
      "step": 75
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 0.11245721578598022,
      "learning_rate": 0.00015347962859990744,
      "loss": 0.3914,
      "step": 76
    },
    {
      "epoch": 0.35648148148148145,
      "grad_norm": 0.12136757373809814,
      "learning_rate": 0.00015218482555779165,
      "loss": 0.4091,
      "step": 77
    },
    {
      "epoch": 0.3611111111111111,
      "grad_norm": 0.12102342396974564,
      "learning_rate": 0.00015087788580152206,
      "loss": 0.388,
      "step": 78
    },
    {
      "epoch": 0.36574074074074076,
      "grad_norm": 0.12198664247989655,
      "learning_rate": 0.00014955911328831355,
      "loss": 0.4031,
      "step": 79
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.12982136011123657,
      "learning_rate": 0.00014822881472734562,
      "loss": 0.409,
      "step": 80
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.134304016828537,
      "learning_rate": 0.00014688729950843035,
      "loss": 0.3815,
      "step": 81
    },
    {
      "epoch": 0.37962962962962965,
      "grad_norm": 0.11940658837556839,
      "learning_rate": 0.0001455348796300571,
      "loss": 0.4119,
      "step": 82
    },
    {
      "epoch": 0.38425925925925924,
      "grad_norm": 0.13899056613445282,
      "learning_rate": 0.0001441718696268307,
      "loss": 0.485,
      "step": 83
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.12257847934961319,
      "learning_rate": 0.0001427985864963193,
      "loss": 0.3877,
      "step": 84
    },
    {
      "epoch": 0.39351851851851855,
      "grad_norm": 0.11885726451873779,
      "learning_rate": 0.00014141534962532984,
      "loss": 0.4371,
      "step": 85
    },
    {
      "epoch": 0.39814814814814814,
      "grad_norm": 0.12147360295057297,
      "learning_rate": 0.0001400224807156278,
      "loss": 0.4201,
      "step": 86
    },
    {
      "epoch": 0.4027777777777778,
      "grad_norm": 0.1597365140914917,
      "learning_rate": 0.0001386203037091183,
      "loss": 0.3968,
      "step": 87
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.13029275834560394,
      "learning_rate": 0.00013720914471250644,
      "loss": 0.3683,
      "step": 88
    },
    {
      "epoch": 0.41203703703703703,
      "grad_norm": 0.1297105997800827,
      "learning_rate": 0.0001357893319214542,
      "loss": 0.4314,
      "step": 89
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.127646341919899,
      "learning_rate": 0.00013436119554425133,
      "loss": 0.4263,
      "step": 90
    },
    {
      "epoch": 0.4212962962962963,
      "grad_norm": 0.16037966310977936,
      "learning_rate": 0.00013292506772501819,
      "loss": 0.3966,
      "step": 91
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 0.13694526255130768,
      "learning_rate": 0.0001314812824664585,
      "loss": 0.4312,
      "step": 92
    },
    {
      "epoch": 0.4305555555555556,
      "grad_norm": 0.138661727309227,
      "learning_rate": 0.0001300301755521798,
      "loss": 0.4041,
      "step": 93
    },
    {
      "epoch": 0.4351851851851852,
      "grad_norm": 0.1248079240322113,
      "learning_rate": 0.0001285720844685996,
      "loss": 0.4191,
      "step": 94
    },
    {
      "epoch": 0.4398148148148148,
      "grad_norm": 0.14905443787574768,
      "learning_rate": 0.00012710734832645557,
      "loss": 0.4246,
      "step": 95
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.1143692284822464,
      "learning_rate": 0.00012563630778193805,
      "loss": 0.392,
      "step": 96
    },
    {
      "epoch": 0.44907407407407407,
      "grad_norm": 0.13354505598545074,
      "learning_rate": 0.00012415930495746302,
      "loss": 0.3888,
      "step": 97
    },
    {
      "epoch": 0.4537037037037037,
      "grad_norm": 0.12897755205631256,
      "learning_rate": 0.00012267668336210413,
      "loss": 0.4005,
      "step": 98
    },
    {
      "epoch": 0.4583333333333333,
      "grad_norm": 0.13209104537963867,
      "learning_rate": 0.00012118878781170214,
      "loss": 0.4388,
      "step": 99
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 0.1058369129896164,
      "learning_rate": 0.00011969596434867063,
      "loss": 0.3768,
      "step": 100
    },
    {
      "epoch": 0.4675925925925926,
      "grad_norm": 0.1227889209985733,
      "learning_rate": 0.00011819856016151615,
      "loss": 0.4185,
      "step": 101
    },
    {
      "epoch": 0.4722222222222222,
      "grad_norm": 0.12500321865081787,
      "learning_rate": 0.00011669692350409223,
      "loss": 0.4384,
      "step": 102
    },
    {
      "epoch": 0.47685185185185186,
      "grad_norm": 0.11348072439432144,
      "learning_rate": 0.00011519140361460509,
      "loss": 0.3781,
      "step": 103
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.10950199514627457,
      "learning_rate": 0.00011368235063439103,
      "loss": 0.4361,
      "step": 104
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 0.1136554479598999,
      "learning_rate": 0.00011217011552648316,
      "loss": 0.3969,
      "step": 105
    },
    {
      "epoch": 0.49074074074074076,
      "grad_norm": 0.11277665942907333,
      "learning_rate": 0.00011065504999398762,
      "loss": 0.3661,
      "step": 106
    },
    {
      "epoch": 0.49537037037037035,
      "grad_norm": 0.12983547151088715,
      "learning_rate": 0.00010913750639828711,
      "loss": 0.4564,
      "step": 107
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.11856082826852798,
      "learning_rate": 0.00010761783767709182,
      "loss": 0.3701,
      "step": 108
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.4069269299507141,
      "eval_runtime": 16.2051,
      "eval_samples_per_second": 22.462,
      "eval_steps_per_second": 2.839,
      "step": 108
    },
    {
      "epoch": 0.5046296296296297,
      "grad_norm": 0.1263894885778427,
      "learning_rate": 0.00010609639726235591,
      "loss": 0.3944,
      "step": 109
    },
    {
      "epoch": 0.5092592592592593,
      "grad_norm": 0.11527308821678162,
      "learning_rate": 0.00010457353899807946,
      "loss": 0.3595,
      "step": 110
    },
    {
      "epoch": 0.5138888888888888,
      "grad_norm": 0.13389469683170319,
      "learning_rate": 0.00010304961705801415,
      "loss": 0.3942,
      "step": 111
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.13051699101924896,
      "learning_rate": 0.0001015249858632926,
      "loss": 0.4191,
      "step": 112
    },
    {
      "epoch": 0.5231481481481481,
      "grad_norm": 0.11771571636199951,
      "learning_rate": 0.0001,
      "loss": 0.3562,
      "step": 113
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 0.12572339177131653,
      "learning_rate": 9.847501413670742e-05,
      "loss": 0.4627,
      "step": 114
    },
    {
      "epoch": 0.5324074074074074,
      "grad_norm": 0.11780008673667908,
      "learning_rate": 9.695038294198589e-05,
      "loss": 0.3913,
      "step": 115
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 0.12987138330936432,
      "learning_rate": 9.542646100192056e-05,
      "loss": 0.3927,
      "step": 116
    },
    {
      "epoch": 0.5416666666666666,
      "grad_norm": 0.11142438650131226,
      "learning_rate": 9.390360273764411e-05,
      "loss": 0.3878,
      "step": 117
    },
    {
      "epoch": 0.5462962962962963,
      "grad_norm": 0.12454476207494736,
      "learning_rate": 9.238216232290822e-05,
      "loss": 0.3821,
      "step": 118
    },
    {
      "epoch": 0.5509259259259259,
      "grad_norm": 0.1253252476453781,
      "learning_rate": 9.08624936017129e-05,
      "loss": 0.3993,
      "step": 119
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.12194947898387909,
      "learning_rate": 8.93449500060124e-05,
      "loss": 0.3954,
      "step": 120
    },
    {
      "epoch": 0.5601851851851852,
      "grad_norm": 0.1179381012916565,
      "learning_rate": 8.782988447351685e-05,
      "loss": 0.3478,
      "step": 121
    },
    {
      "epoch": 0.5648148148148148,
      "grad_norm": 0.1392665058374405,
      "learning_rate": 8.6317649365609e-05,
      "loss": 0.4455,
      "step": 122
    },
    {
      "epoch": 0.5694444444444444,
      "grad_norm": 0.12414383888244629,
      "learning_rate": 8.480859638539492e-05,
      "loss": 0.3763,
      "step": 123
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 0.1223541721701622,
      "learning_rate": 8.33030764959078e-05,
      "loss": 0.3973,
      "step": 124
    },
    {
      "epoch": 0.5787037037037037,
      "grad_norm": 0.11729186028242111,
      "learning_rate": 8.180143983848387e-05,
      "loss": 0.3639,
      "step": 125
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 0.13269482553005219,
      "learning_rate": 8.030403565132942e-05,
      "loss": 0.4481,
      "step": 126
    },
    {
      "epoch": 0.5879629629629629,
      "grad_norm": 0.12841080129146576,
      "learning_rate": 7.881121218829787e-05,
      "loss": 0.4442,
      "step": 127
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.11603926122188568,
      "learning_rate": 7.732331663789592e-05,
      "loss": 0.447,
      "step": 128
    },
    {
      "epoch": 0.5972222222222222,
      "grad_norm": 0.12863722443580627,
      "learning_rate": 7.584069504253703e-05,
      "loss": 0.3837,
      "step": 129
    },
    {
      "epoch": 0.6018518518518519,
      "grad_norm": 0.1303769052028656,
      "learning_rate": 7.436369221806201e-05,
      "loss": 0.4251,
      "step": 130
    },
    {
      "epoch": 0.6064814814814815,
      "grad_norm": 0.12298469245433807,
      "learning_rate": 7.289265167354449e-05,
      "loss": 0.3873,
      "step": 131
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.13410842418670654,
      "learning_rate": 7.142791553140045e-05,
      "loss": 0.3767,
      "step": 132
    },
    {
      "epoch": 0.6157407407407407,
      "grad_norm": 0.13108515739440918,
      "learning_rate": 6.996982444782021e-05,
      "loss": 0.3785,
      "step": 133
    },
    {
      "epoch": 0.6203703703703703,
      "grad_norm": 0.12329968065023422,
      "learning_rate": 6.851871753354153e-05,
      "loss": 0.4202,
      "step": 134
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.12874025106430054,
      "learning_rate": 6.707493227498188e-05,
      "loss": 0.4251,
      "step": 135
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.13529813289642334,
      "learning_rate": 6.563880445574873e-05,
      "loss": 0.4349,
      "step": 136
    },
    {
      "epoch": 0.6342592592592593,
      "grad_norm": 0.12647311389446259,
      "learning_rate": 6.421066807854584e-05,
      "loss": 0.3653,
      "step": 137
    },
    {
      "epoch": 0.6388888888888888,
      "grad_norm": 0.15596190094947815,
      "learning_rate": 6.279085528749359e-05,
      "loss": 0.4317,
      "step": 138
    },
    {
      "epoch": 0.6435185185185185,
      "grad_norm": 0.11850515007972717,
      "learning_rate": 6.137969629088173e-05,
      "loss": 0.344,
      "step": 139
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 0.12194859981536865,
      "learning_rate": 5.9977519284372194e-05,
      "loss": 0.3983,
      "step": 140
    },
    {
      "epoch": 0.6527777777777778,
      "grad_norm": 0.13437777757644653,
      "learning_rate": 5.8584650374670135e-05,
      "loss": 0.4072,
      "step": 141
    },
    {
      "epoch": 0.6574074074074074,
      "grad_norm": 0.13930705189704895,
      "learning_rate": 5.720141350368072e-05,
      "loss": 0.3578,
      "step": 142
    },
    {
      "epoch": 0.6620370370370371,
      "grad_norm": 0.13413161039352417,
      "learning_rate": 5.582813037316927e-05,
      "loss": 0.4193,
      "step": 143
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.11998701095581055,
      "learning_rate": 5.446512036994287e-05,
      "loss": 0.383,
      "step": 144
    },
    {
      "epoch": 0.6712962962962963,
      "grad_norm": 0.14133970439434052,
      "learning_rate": 5.3112700491569666e-05,
      "loss": 0.421,
      "step": 145
    },
    {
      "epoch": 0.6759259259259259,
      "grad_norm": 0.13386432826519012,
      "learning_rate": 5.177118527265438e-05,
      "loss": 0.4164,
      "step": 146
    },
    {
      "epoch": 0.6805555555555556,
      "grad_norm": 0.12818817794322968,
      "learning_rate": 5.044088671168644e-05,
      "loss": 0.3719,
      "step": 147
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 0.13193628191947937,
      "learning_rate": 4.912211419847794e-05,
      "loss": 0.3729,
      "step": 148
    },
    {
      "epoch": 0.6898148148148148,
      "grad_norm": 0.1342621147632599,
      "learning_rate": 4.7815174442208354e-05,
      "loss": 0.4562,
      "step": 149
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 0.13930144906044006,
      "learning_rate": 4.652037140009259e-05,
      "loss": 0.4098,
      "step": 150
    },
    {
      "epoch": 0.6990740740740741,
      "grad_norm": 0.15138937532901764,
      "learning_rate": 4.523800620668921e-05,
      "loss": 0.4521,
      "step": 151
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.12120551615953445,
      "learning_rate": 4.3968377103865024e-05,
      "loss": 0.4156,
      "step": 152
    },
    {
      "epoch": 0.7083333333333334,
      "grad_norm": 0.1313461810350418,
      "learning_rate": 4.271177937143245e-05,
      "loss": 0.4086,
      "step": 153
    },
    {
      "epoch": 0.7129629629629629,
      "grad_norm": 0.12950317561626434,
      "learning_rate": 4.146850525847579e-05,
      "loss": 0.3993,
      "step": 154
    },
    {
      "epoch": 0.7175925925925926,
      "grad_norm": 0.11331982165575027,
      "learning_rate": 4.023884391538244e-05,
      "loss": 0.3846,
      "step": 155
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.12068940699100494,
      "learning_rate": 3.902308132659457e-05,
      "loss": 0.356,
      "step": 156
    },
    {
      "epoch": 0.7268518518518519,
      "grad_norm": 0.12462019920349121,
      "learning_rate": 3.7821500244097274e-05,
      "loss": 0.4099,
      "step": 157
    },
    {
      "epoch": 0.7314814814814815,
      "grad_norm": 0.12054712325334549,
      "learning_rate": 3.663438012165848e-05,
      "loss": 0.4046,
      "step": 158
    },
    {
      "epoch": 0.7361111111111112,
      "grad_norm": 0.1289607435464859,
      "learning_rate": 3.5461997049835914e-05,
      "loss": 0.37,
      "step": 159
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.14201810956001282,
      "learning_rate": 3.430462369176619e-05,
      "loss": 0.407,
      "step": 160
    },
    {
      "epoch": 0.7453703703703703,
      "grad_norm": 0.1232706606388092,
      "learning_rate": 3.316252921975116e-05,
      "loss": 0.3583,
      "step": 161
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.12519972026348114,
      "learning_rate": 3.203597925265598e-05,
      "loss": 0.3278,
      "step": 162
    },
    {
      "epoch": 0.7546296296296297,
      "grad_norm": 0.12523451447486877,
      "learning_rate": 3.092523579413372e-05,
      "loss": 0.3919,
      "step": 163
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 0.12420208007097244,
      "learning_rate": 2.98305571716907e-05,
      "loss": 0.3761,
      "step": 164
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 0.13486765325069427,
      "learning_rate": 2.875219797660681e-05,
      "loss": 0.3933,
      "step": 165
    },
    {
      "epoch": 0.7685185185185185,
      "grad_norm": 0.1384674608707428,
      "learning_rate": 2.769040900472488e-05,
      "loss": 0.4366,
      "step": 166
    },
    {
      "epoch": 0.7731481481481481,
      "grad_norm": 0.1498284786939621,
      "learning_rate": 2.6645437198122502e-05,
      "loss": 0.4676,
      "step": 167
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.1257813721895218,
      "learning_rate": 2.5617525587680402e-05,
      "loss": 0.3873,
      "step": 168
    },
    {
      "epoch": 0.7824074074074074,
      "grad_norm": 0.12799781560897827,
      "learning_rate": 2.4606913236560282e-05,
      "loss": 0.3943,
      "step": 169
    },
    {
      "epoch": 0.7870370370370371,
      "grad_norm": 0.12439963966608047,
      "learning_rate": 2.3613835184605525e-05,
      "loss": 0.394,
      "step": 170
    },
    {
      "epoch": 0.7916666666666666,
      "grad_norm": 0.11842609196901321,
      "learning_rate": 2.2638522393677563e-05,
      "loss": 0.3348,
      "step": 171
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 0.14370441436767578,
      "learning_rate": 2.1681201693940668e-05,
      "loss": 0.4303,
      "step": 172
    },
    {
      "epoch": 0.8009259259259259,
      "grad_norm": 0.137470081448555,
      "learning_rate": 2.074209573110769e-05,
      "loss": 0.3785,
      "step": 173
    },
    {
      "epoch": 0.8055555555555556,
      "grad_norm": 0.1420845240354538,
      "learning_rate": 1.982142291465896e-05,
      "loss": 0.3943,
      "step": 174
    },
    {
      "epoch": 0.8101851851851852,
      "grad_norm": 0.15280939638614655,
      "learning_rate": 1.891939736704641e-05,
      "loss": 0.4234,
      "step": 175
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.12755198776721954,
      "learning_rate": 1.8036228873894746e-05,
      "loss": 0.3992,
      "step": 176
    },
    {
      "epoch": 0.8194444444444444,
      "grad_norm": 0.12794767320156097,
      "learning_rate": 1.7172122835211337e-05,
      "loss": 0.3598,
      "step": 177
    },
    {
      "epoch": 0.8240740740740741,
      "grad_norm": 0.15256819128990173,
      "learning_rate": 1.6327280217615792e-05,
      "loss": 0.3803,
      "step": 178
    },
    {
      "epoch": 0.8287037037037037,
      "grad_norm": 0.1349879652261734,
      "learning_rate": 1.5501897507601014e-05,
      "loss": 0.4246,
      "step": 179
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.13489031791687012,
      "learning_rate": 1.4696166665835853e-05,
      "loss": 0.3833,
      "step": 180
    },
    {
      "epoch": 0.8379629629629629,
      "grad_norm": 0.13907630741596222,
      "learning_rate": 1.3910275082520573e-05,
      "loss": 0.3788,
      "step": 181
    },
    {
      "epoch": 0.8425925925925926,
      "grad_norm": 0.13649378716945648,
      "learning_rate": 1.3144405533805138e-05,
      "loss": 0.4687,
      "step": 182
    },
    {
      "epoch": 0.8472222222222222,
      "grad_norm": 0.1456245630979538,
      "learning_rate": 1.2398736139280686e-05,
      "loss": 0.3921,
      "step": 183
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 0.12474421411752701,
      "learning_rate": 1.167344032055394e-05,
      "loss": 0.4069,
      "step": 184
    },
    {
      "epoch": 0.8564814814814815,
      "grad_norm": 0.15731000900268555,
      "learning_rate": 1.096868676091425e-05,
      "loss": 0.4182,
      "step": 185
    },
    {
      "epoch": 0.8611111111111112,
      "grad_norm": 0.12348570674657822,
      "learning_rate": 1.02846393661026e-05,
      "loss": 0.2944,
      "step": 186
    },
    {
      "epoch": 0.8657407407407407,
      "grad_norm": 0.14169996976852417,
      "learning_rate": 9.62145722619182e-06,
      "loss": 0.4497,
      "step": 187
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 0.14467938244342804,
      "learning_rate": 8.979294578586738e-06,
      "loss": 0.3987,
      "step": 188
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.13816998898983002,
      "learning_rate": 8.358300772152849e-06,
      "loss": 0.4331,
      "step": 189
    },
    {
      "epoch": 0.8796296296296297,
      "grad_norm": 0.12907293438911438,
      "learning_rate": 7.758620232482084e-06,
      "loss": 0.408,
      "step": 190
    },
    {
      "epoch": 0.8842592592592593,
      "grad_norm": 0.13425540924072266,
      "learning_rate": 7.180392428303395e-06,
      "loss": 0.41,
      "step": 191
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.12629586458206177,
      "learning_rate": 6.623751839046455e-06,
      "loss": 0.383,
      "step": 192
    },
    {
      "epoch": 0.8935185185185185,
      "grad_norm": 0.12552037835121155,
      "learning_rate": 6.0888279235653214e-06,
      "loss": 0.3999,
      "step": 193
    },
    {
      "epoch": 0.8981481481481481,
      "grad_norm": 0.1186065599322319,
      "learning_rate": 5.575745090030138e-06,
      "loss": 0.3515,
      "step": 194
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 0.12220544368028641,
      "learning_rate": 5.084622666993244e-06,
      "loss": 0.3457,
      "step": 195
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 0.12332714349031448,
      "learning_rate": 4.61557487563673e-06,
      "loss": 0.3682,
      "step": 196
    },
    {
      "epoch": 0.9120370370370371,
      "grad_norm": 0.14207704365253448,
      "learning_rate": 4.168710803207865e-06,
      "loss": 0.4121,
      "step": 197
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 0.15227369964122772,
      "learning_rate": 3.7441343776484117e-06,
      "loss": 0.4389,
      "step": 198
    },
    {
      "epoch": 0.9212962962962963,
      "grad_norm": 0.11998874694108963,
      "learning_rate": 3.3419443434240083e-06,
      "loss": 0.387,
      "step": 199
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.12720437347888947,
      "learning_rate": 2.9622342385589254e-06,
      "loss": 0.4549,
      "step": 200
    },
    {
      "epoch": 0.9305555555555556,
      "grad_norm": 0.11992080509662628,
      "learning_rate": 2.6050923728818787e-06,
      "loss": 0.3897,
      "step": 201
    },
    {
      "epoch": 0.9351851851851852,
      "grad_norm": 0.13751375675201416,
      "learning_rate": 2.2706018074875045e-06,
      "loss": 0.446,
      "step": 202
    },
    {
      "epoch": 0.9398148148148148,
      "grad_norm": 0.13101902604103088,
      "learning_rate": 1.9588403354188325e-06,
      "loss": 0.3896,
      "step": 203
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 0.16959664225578308,
      "learning_rate": 1.6698804635747579e-06,
      "loss": 0.3973,
      "step": 204
    },
    {
      "epoch": 0.9490740740740741,
      "grad_norm": 0.12849944829940796,
      "learning_rate": 1.4037893958469995e-06,
      "loss": 0.4292,
      "step": 205
    },
    {
      "epoch": 0.9537037037037037,
      "grad_norm": 0.1358756721019745,
      "learning_rate": 1.160629017490389e-06,
      "loss": 0.4263,
      "step": 206
    },
    {
      "epoch": 0.9583333333333334,
      "grad_norm": 0.13140828907489777,
      "learning_rate": 9.404558807301067e-07,
      "loss": 0.4185,
      "step": 207
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.11467701196670532,
      "learning_rate": 7.433211916092142e-07,
      "loss": 0.3713,
      "step": 208
    },
    {
      "epoch": 0.9675925925925926,
      "grad_norm": 0.12362132221460342,
      "learning_rate": 5.69270798079613e-07,
      "loss": 0.3453,
      "step": 209
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 0.12156709283590317,
      "learning_rate": 4.1834517933907467e-07,
      "loss": 0.3788,
      "step": 210
    },
    {
      "epoch": 0.9768518518518519,
      "grad_norm": 0.12119793891906738,
      "learning_rate": 2.9057943641693785e-07,
      "loss": 0.3662,
      "step": 211
    },
    {
      "epoch": 0.9814814814814815,
      "grad_norm": 0.12225915491580963,
      "learning_rate": 1.8600328401061629e-07,
      "loss": 0.3854,
      "step": 212
    },
    {
      "epoch": 0.9861111111111112,
      "grad_norm": 0.1316448301076889,
      "learning_rate": 1.0464104357477133e-07,
      "loss": 0.3872,
      "step": 213
    },
    {
      "epoch": 0.9907407407407407,
      "grad_norm": 0.11485154181718826,
      "learning_rate": 4.651163766484779e-08,
      "loss": 0.3017,
      "step": 214
    },
    {
      "epoch": 0.9953703703703703,
      "grad_norm": 0.11364009231328964,
      "learning_rate": 1.1628585536216374e-08,
      "loss": 0.3339,
      "step": 215
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.13067637383937836,
      "learning_rate": 0.0,
      "loss": 0.3867,
      "step": 216
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.39731329679489136,
      "eval_runtime": 16.3193,
      "eval_samples_per_second": 22.305,
      "eval_steps_per_second": 2.819,
      "step": 216
    }
  ],
  "logging_steps": 1,
  "max_steps": 216,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.356226766877491e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}