{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09780548933308882,
  "eval_steps": 34,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004890274466654441,
      "grad_norm": 0.34075865149497986,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.3759,
      "step": 1
    },
    {
      "epoch": 0.0004890274466654441,
      "eval_loss": 1.4345602989196777,
      "eval_runtime": 756.5177,
      "eval_samples_per_second": 3.414,
      "eval_steps_per_second": 1.138,
      "step": 1
    },
    {
      "epoch": 0.0009780548933308881,
      "grad_norm": 0.4255630671977997,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.4716,
      "step": 2
    },
    {
      "epoch": 0.0014670823399963323,
      "grad_norm": 0.3547780513763428,
      "learning_rate": 2e-05,
      "loss": 1.5202,
      "step": 3
    },
    {
      "epoch": 0.0019561097866617762,
      "grad_norm": 0.31101933121681213,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.3129,
      "step": 4
    },
    {
      "epoch": 0.0024451372333272204,
      "grad_norm": 0.3006742596626282,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.2779,
      "step": 5
    },
    {
      "epoch": 0.0029341646799926646,
      "grad_norm": 0.3246765434741974,
      "learning_rate": 4e-05,
      "loss": 1.3872,
      "step": 6
    },
    {
      "epoch": 0.0034231921266581087,
      "grad_norm": 0.3884378969669342,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.354,
      "step": 7
    },
    {
      "epoch": 0.0039122195733235525,
      "grad_norm": 0.5120812058448792,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.765,
      "step": 8
    },
    {
      "epoch": 0.004401247019988997,
      "grad_norm": 0.41704061627388,
      "learning_rate": 6e-05,
      "loss": 1.2998,
      "step": 9
    },
    {
      "epoch": 0.004890274466654441,
      "grad_norm": 0.3975231349468231,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.3667,
      "step": 10
    },
    {
      "epoch": 0.005379301913319885,
      "grad_norm": 0.5725282430648804,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.4608,
      "step": 11
    },
    {
      "epoch": 0.005868329359985329,
      "grad_norm": 0.4843478202819824,
      "learning_rate": 8e-05,
      "loss": 1.3698,
      "step": 12
    },
    {
      "epoch": 0.006357356806650773,
      "grad_norm": 0.3960322439670563,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.2011,
      "step": 13
    },
    {
      "epoch": 0.0068463842533162175,
      "grad_norm": 0.6137775778770447,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.5016,
      "step": 14
    },
    {
      "epoch": 0.007335411699981661,
      "grad_norm": 0.6010208129882812,
      "learning_rate": 0.0001,
      "loss": 1.4161,
      "step": 15
    },
    {
      "epoch": 0.007824439146647105,
      "grad_norm": 0.8341742157936096,
      "learning_rate": 0.00010666666666666667,
      "loss": 1.4157,
      "step": 16
    },
    {
      "epoch": 0.00831346659331255,
      "grad_norm": 0.42079266905784607,
      "learning_rate": 0.00011333333333333334,
      "loss": 1.2893,
      "step": 17
    },
    {
      "epoch": 0.008802494039977994,
      "grad_norm": 0.45083093643188477,
      "learning_rate": 0.00012,
      "loss": 1.2956,
      "step": 18
    },
    {
      "epoch": 0.009291521486643438,
      "grad_norm": 0.46682217717170715,
      "learning_rate": 0.00012666666666666666,
      "loss": 1.3902,
      "step": 19
    },
    {
      "epoch": 0.009780548933308882,
      "grad_norm": 0.7860361933708191,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.3736,
      "step": 20
    },
    {
      "epoch": 0.010269576379974325,
      "grad_norm": 0.26767078042030334,
      "learning_rate": 0.00014,
      "loss": 1.1387,
      "step": 21
    },
    {
      "epoch": 0.01075860382663977,
      "grad_norm": 0.9698910713195801,
      "learning_rate": 0.00014666666666666666,
      "loss": 1.2275,
      "step": 22
    },
    {
      "epoch": 0.011247631273305215,
      "grad_norm": 0.37882354855537415,
      "learning_rate": 0.00015333333333333334,
      "loss": 1.0338,
      "step": 23
    },
    {
      "epoch": 0.011736658719970658,
      "grad_norm": 0.4246285855770111,
      "learning_rate": 0.00016,
      "loss": 0.9779,
      "step": 24
    },
    {
      "epoch": 0.012225686166636102,
      "grad_norm": 0.6815544962882996,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.1132,
      "step": 25
    },
    {
      "epoch": 0.012714713613301546,
      "grad_norm": 0.5367336869239807,
      "learning_rate": 0.00017333333333333334,
      "loss": 1.0901,
      "step": 26
    },
    {
      "epoch": 0.013203741059966991,
      "grad_norm": 0.38169288635253906,
      "learning_rate": 0.00018,
      "loss": 1.0774,
      "step": 27
    },
    {
      "epoch": 0.013692768506632435,
      "grad_norm": 0.764456570148468,
      "learning_rate": 0.0001866666666666667,
      "loss": 1.0737,
      "step": 28
    },
    {
      "epoch": 0.014181795953297879,
      "grad_norm": 0.39200517535209656,
      "learning_rate": 0.00019333333333333333,
      "loss": 1.0272,
      "step": 29
    },
    {
      "epoch": 0.014670823399963322,
      "grad_norm": 0.372561514377594,
      "learning_rate": 0.0002,
      "loss": 1.0901,
      "step": 30
    },
    {
      "epoch": 0.015159850846628768,
      "grad_norm": 0.43094900250434875,
      "learning_rate": 0.00019998292504580528,
      "loss": 1.0589,
      "step": 31
    },
    {
      "epoch": 0.01564887829329421,
      "grad_norm": 0.49306023120880127,
      "learning_rate": 0.0001999317060143023,
      "loss": 1.2902,
      "step": 32
    },
    {
      "epoch": 0.016137905739959654,
      "grad_norm": 0.7269837856292725,
      "learning_rate": 0.0001998463603967434,
      "loss": 1.0952,
      "step": 33
    },
    {
      "epoch": 0.0166269331866251,
      "grad_norm": 0.3524138033390045,
      "learning_rate": 0.00019972691733857883,
      "loss": 1.2609,
      "step": 34
    },
    {
      "epoch": 0.0166269331866251,
      "eval_loss": 1.132264256477356,
      "eval_runtime": 759.3417,
      "eval_samples_per_second": 3.402,
      "eval_steps_per_second": 1.134,
      "step": 34
    },
    {
      "epoch": 0.017115960633290545,
      "grad_norm": 0.382266104221344,
      "learning_rate": 0.00019957341762950344,
      "loss": 1.2098,
      "step": 35
    },
    {
      "epoch": 0.017604988079955988,
      "grad_norm": 0.3929167091846466,
      "learning_rate": 0.0001993859136895274,
      "loss": 1.079,
      "step": 36
    },
    {
      "epoch": 0.018094015526621432,
      "grad_norm": 0.42827725410461426,
      "learning_rate": 0.00019916446955107428,
      "loss": 1.1863,
      "step": 37
    },
    {
      "epoch": 0.018583042973286876,
      "grad_norm": 0.4391894042491913,
      "learning_rate": 0.0001989091608371146,
      "loss": 1.0664,
      "step": 38
    },
    {
      "epoch": 0.01907207041995232,
      "grad_norm": 0.29932713508605957,
      "learning_rate": 0.00019862007473534025,
      "loss": 1.0486,
      "step": 39
    },
    {
      "epoch": 0.019561097866617763,
      "grad_norm": 0.35039955377578735,
      "learning_rate": 0.0001982973099683902,
      "loss": 1.2274,
      "step": 40
    },
    {
      "epoch": 0.020050125313283207,
      "grad_norm": 0.3043316602706909,
      "learning_rate": 0.0001979409767601366,
      "loss": 1.2289,
      "step": 41
    },
    {
      "epoch": 0.02053915275994865,
      "grad_norm": 0.35605862736701965,
      "learning_rate": 0.00019755119679804367,
      "loss": 1.1258,
      "step": 42
    },
    {
      "epoch": 0.021028180206614098,
      "grad_norm": 0.3062782883644104,
      "learning_rate": 0.0001971281031916114,
      "loss": 1.0944,
      "step": 43
    },
    {
      "epoch": 0.02151720765327954,
      "grad_norm": 0.5709540247917175,
      "learning_rate": 0.00019667184042691875,
      "loss": 1.1156,
      "step": 44
    },
    {
      "epoch": 0.022006235099944985,
      "grad_norm": 0.2735868990421295,
      "learning_rate": 0.00019618256431728194,
      "loss": 1.1004,
      "step": 45
    },
    {
      "epoch": 0.02249526254661043,
      "grad_norm": 0.2974896728992462,
      "learning_rate": 0.0001956604419500441,
      "loss": 1.1905,
      "step": 46
    },
    {
      "epoch": 0.022984289993275873,
      "grad_norm": 0.2619563639163971,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.9966,
      "step": 47
    },
    {
      "epoch": 0.023473317439941317,
      "grad_norm": 0.4926609396934509,
      "learning_rate": 0.00019451838281608197,
      "loss": 1.1663,
      "step": 48
    },
    {
      "epoch": 0.02396234488660676,
      "grad_norm": 0.5267955660820007,
      "learning_rate": 0.00019389883606150566,
      "loss": 1.2211,
      "step": 49
    },
    {
      "epoch": 0.024451372333272204,
      "grad_norm": 0.3230949342250824,
      "learning_rate": 0.00019324722294043558,
      "loss": 1.1212,
      "step": 50
    },
    {
      "epoch": 0.024940399779937648,
      "grad_norm": 0.23493480682373047,
      "learning_rate": 0.00019256376597815564,
      "loss": 1.0893,
      "step": 51
    },
    {
      "epoch": 0.02542942722660309,
      "grad_norm": 0.40444502234458923,
      "learning_rate": 0.00019184869857459232,
      "loss": 1.2533,
      "step": 52
    },
    {
      "epoch": 0.02591845467326854,
      "grad_norm": 0.35901519656181335,
      "learning_rate": 0.00019110226492460885,
      "loss": 1.1222,
      "step": 53
    },
    {
      "epoch": 0.026407482119933982,
      "grad_norm": 0.3760276734828949,
      "learning_rate": 0.0001903247199346129,
      "loss": 1.2518,
      "step": 54
    },
    {
      "epoch": 0.026896509566599426,
      "grad_norm": 0.25572359561920166,
      "learning_rate": 0.00018951632913550626,
      "loss": 0.9859,
      "step": 55
    },
    {
      "epoch": 0.02738553701326487,
      "grad_norm": 0.2863282561302185,
      "learning_rate": 0.0001886773685920062,
      "loss": 1.0886,
      "step": 56
    },
    {
      "epoch": 0.027874564459930314,
      "grad_norm": 0.287009596824646,
      "learning_rate": 0.0001878081248083698,
      "loss": 1.0499,
      "step": 57
    },
    {
      "epoch": 0.028363591906595757,
      "grad_norm": 0.28609392046928406,
      "learning_rate": 0.00018690889463055283,
      "loss": 1.1628,
      "step": 58
    },
    {
      "epoch": 0.0288526193532612,
      "grad_norm": 0.30997133255004883,
      "learning_rate": 0.00018597998514483725,
      "loss": 1.0111,
      "step": 59
    },
    {
      "epoch": 0.029341646799926645,
      "grad_norm": 0.31929582357406616,
      "learning_rate": 0.00018502171357296144,
      "loss": 1.0741,
      "step": 60
    },
    {
      "epoch": 0.02983067424659209,
      "grad_norm": 0.38454172015190125,
      "learning_rate": 0.00018403440716378928,
      "loss": 1.1337,
      "step": 61
    },
    {
      "epoch": 0.030319701693257536,
      "grad_norm": 0.2676106095314026,
      "learning_rate": 0.00018301840308155507,
      "loss": 1.1543,
      "step": 62
    },
    {
      "epoch": 0.03080872913992298,
      "grad_norm": 0.36240771412849426,
      "learning_rate": 0.00018197404829072215,
      "loss": 1.1891,
      "step": 63
    },
    {
      "epoch": 0.03129775658658842,
      "grad_norm": 0.49118804931640625,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.3306,
      "step": 64
    },
    {
      "epoch": 0.03178678403325386,
      "grad_norm": 0.4062592387199402,
      "learning_rate": 0.000179801722728024,
      "loss": 1.0769,
      "step": 65
    },
    {
      "epoch": 0.03227581147991931,
      "grad_norm": 0.25919100642204285,
      "learning_rate": 0.00017867449380334834,
      "loss": 1.0098,
      "step": 66
    },
    {
      "epoch": 0.03276483892658476,
      "grad_norm": 0.458816796541214,
      "learning_rate": 0.00017752039761111297,
      "loss": 1.1585,
      "step": 67
    },
    {
      "epoch": 0.0332538663732502,
      "grad_norm": 0.35210469365119934,
      "learning_rate": 0.00017633982827411032,
      "loss": 1.1674,
      "step": 68
    },
    {
      "epoch": 0.0332538663732502,
      "eval_loss": 1.098181128501892,
      "eval_runtime": 759.3536,
      "eval_samples_per_second": 3.402,
      "eval_steps_per_second": 1.134,
      "step": 68
    },
    {
      "epoch": 0.033742893819915645,
      "grad_norm": 0.28391891717910767,
      "learning_rate": 0.00017513318895568737,
      "loss": 1.1126,
      "step": 69
    },
    {
      "epoch": 0.03423192126658109,
      "grad_norm": 0.6352168321609497,
      "learning_rate": 0.00017390089172206592,
      "loss": 1.0541,
      "step": 70
    },
    {
      "epoch": 0.03472094871324653,
      "grad_norm": 0.37239882349967957,
      "learning_rate": 0.00017264335740162242,
      "loss": 1.0585,
      "step": 71
    },
    {
      "epoch": 0.035209976159911976,
      "grad_norm": 0.3464653789997101,
      "learning_rate": 0.00017136101544117525,
      "loss": 1.1741,
      "step": 72
    },
    {
      "epoch": 0.03569900360657742,
      "grad_norm": 0.33584925532341003,
      "learning_rate": 0.0001700543037593291,
      "loss": 0.9492,
      "step": 73
    },
    {
      "epoch": 0.036188031053242864,
      "grad_norm": 0.5078179240226746,
      "learning_rate": 0.00016872366859692627,
      "loss": 1.1001,
      "step": 74
    },
    {
      "epoch": 0.03667705849990831,
      "grad_norm": 0.4245125353336334,
      "learning_rate": 0.00016736956436465573,
      "loss": 1.3931,
      "step": 75
    },
    {
      "epoch": 0.03716608594657375,
      "grad_norm": 0.27016469836235046,
      "learning_rate": 0.0001659924534878723,
      "loss": 1.0642,
      "step": 76
    },
    {
      "epoch": 0.037655113393239195,
      "grad_norm": 0.2711539566516876,
      "learning_rate": 0.00016459280624867874,
      "loss": 1.0618,
      "step": 77
    },
    {
      "epoch": 0.03814414083990464,
      "grad_norm": 0.33239468932151794,
      "learning_rate": 0.0001631711006253251,
      "loss": 0.917,
      "step": 78
    },
    {
      "epoch": 0.03863316828657008,
      "grad_norm": 0.31636130809783936,
      "learning_rate": 0.0001617278221289793,
      "loss": 1.088,
      "step": 79
    },
    {
      "epoch": 0.039122195733235526,
      "grad_norm": 0.33746403455734253,
      "learning_rate": 0.00016026346363792567,
      "loss": 1.305,
      "step": 80
    },
    {
      "epoch": 0.03961122317990097,
      "grad_norm": 0.2919120788574219,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.0159,
      "step": 81
    },
    {
      "epoch": 0.040100250626566414,
      "grad_norm": 0.29029732942581177,
      "learning_rate": 0.00015727351400805052,
      "loss": 1.0759,
      "step": 82
    },
    {
      "epoch": 0.04058927807323186,
      "grad_norm": 0.31433698534965515,
      "learning_rate": 0.00015574894393428855,
      "loss": 1.0824,
      "step": 83
    },
    {
      "epoch": 0.0410783055198973,
      "grad_norm": 0.42442116141319275,
      "learning_rate": 0.00015420533564724495,
      "loss": 1.1142,
      "step": 84
    },
    {
      "epoch": 0.041567332966562745,
      "grad_norm": 0.3660612404346466,
      "learning_rate": 0.0001526432162877356,
      "loss": 1.1809,
      "step": 85
    },
    {
      "epoch": 0.042056360413228196,
      "grad_norm": 0.2461833655834198,
      "learning_rate": 0.0001510631193180907,
      "loss": 0.9138,
      "step": 86
    },
    {
      "epoch": 0.04254538785989364,
      "grad_norm": 0.2666703760623932,
      "learning_rate": 0.0001494655843399779,
      "loss": 1.1706,
      "step": 87
    },
    {
      "epoch": 0.04303441530655908,
      "grad_norm": 0.3722439110279083,
      "learning_rate": 0.00014785115691012864,
      "loss": 1.0655,
      "step": 88
    },
    {
      "epoch": 0.04352344275322453,
      "grad_norm": 0.47935646772384644,
      "learning_rate": 0.00014622038835403133,
      "loss": 1.1451,
      "step": 89
    },
    {
      "epoch": 0.04401247019988997,
      "grad_norm": 0.3481261730194092,
      "learning_rate": 0.00014457383557765386,
      "loss": 1.1081,
      "step": 90
    },
    {
      "epoch": 0.044501497646555414,
      "grad_norm": 0.37475869059562683,
      "learning_rate": 0.0001429120608772609,
      "loss": 1.104,
      "step": 91
    },
    {
      "epoch": 0.04499052509322086,
      "grad_norm": 0.22338198125362396,
      "learning_rate": 0.00014123563174739037,
      "loss": 1.1184,
      "step": 92
    },
    {
      "epoch": 0.0454795525398863,
      "grad_norm": 0.24135659635066986,
      "learning_rate": 0.00013954512068705424,
      "loss": 1.0822,
      "step": 93
    },
    {
      "epoch": 0.045968579986551746,
      "grad_norm": 0.3478007912635803,
      "learning_rate": 0.00013784110500423104,
      "loss": 0.9919,
      "step": 94
    },
    {
      "epoch": 0.04645760743321719,
      "grad_norm": 0.3430686891078949,
      "learning_rate": 0.00013612416661871533,
      "loss": 1.2831,
      "step": 95
    },
    {
      "epoch": 0.04694663487988263,
      "grad_norm": 0.36003103852272034,
      "learning_rate": 0.00013439489186339282,
      "loss": 1.2583,
      "step": 96
    },
    {
      "epoch": 0.04743566232654808,
      "grad_norm": 0.3607925474643707,
      "learning_rate": 0.0001326538712840083,
      "loss": 1.0775,
      "step": 97
    },
    {
      "epoch": 0.04792468977321352,
      "grad_norm": 0.2655922770500183,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0783,
      "step": 98
    },
    {
      "epoch": 0.048413717219878964,
      "grad_norm": 0.3258076608181,
      "learning_rate": 0.00012913897468893248,
      "loss": 1.1564,
      "step": 99
    },
    {
      "epoch": 0.04890274466654441,
      "grad_norm": 0.34222668409347534,
      "learning_rate": 0.0001273662990072083,
      "loss": 1.0885,
      "step": 100
    },
    {
      "epoch": 0.04939177211320985,
      "grad_norm": 0.311851441860199,
      "learning_rate": 0.00012558427775944357,
      "loss": 1.0782,
      "step": 101
    },
    {
      "epoch": 0.049880799559875295,
      "grad_norm": 0.31799542903900146,
      "learning_rate": 0.00012379351950426187,
      "loss": 1.0521,
      "step": 102
    },
    {
      "epoch": 0.049880799559875295,
      "eval_loss": 1.088854193687439,
      "eval_runtime": 758.4105,
      "eval_samples_per_second": 3.406,
      "eval_steps_per_second": 1.135,
      "step": 102
    },
    {
      "epoch": 0.05036982700654074,
      "grad_norm": 0.39137113094329834,
      "learning_rate": 0.00012199463578396688,
      "loss": 1.013,
      "step": 103
    },
    {
      "epoch": 0.05085885445320618,
      "grad_norm": 0.3639407753944397,
      "learning_rate": 0.00012018824091570103,
      "loss": 1.2199,
      "step": 104
    },
    {
      "epoch": 0.051347881899871634,
      "grad_norm": 0.26513102650642395,
      "learning_rate": 0.00011837495178165706,
      "loss": 1.1586,
      "step": 105
    },
    {
      "epoch": 0.05183690934653708,
      "grad_norm": 0.24156822264194489,
      "learning_rate": 0.000116555387618413,
      "loss": 1.1001,
      "step": 106
    },
    {
      "epoch": 0.05232593679320252,
      "grad_norm": 0.4346786141395569,
      "learning_rate": 0.00011473016980546377,
      "loss": 1.1021,
      "step": 107
    },
    {
      "epoch": 0.052814964239867965,
      "grad_norm": 0.3028189241886139,
      "learning_rate": 0.00011289992165302035,
      "loss": 1.2426,
      "step": 108
    },
    {
      "epoch": 0.05330399168653341,
      "grad_norm": 0.27877572178840637,
      "learning_rate": 0.00011106526818915008,
      "loss": 1.1498,
      "step": 109
    },
    {
      "epoch": 0.05379301913319885,
      "grad_norm": 0.3245526850223541,
      "learning_rate": 0.00010922683594633021,
      "loss": 1.0992,
      "step": 110
    },
    {
      "epoch": 0.054282046579864296,
      "grad_norm": 0.2573915719985962,
      "learning_rate": 0.00010738525274748741,
      "loss": 1.0028,
      "step": 111
    },
    {
      "epoch": 0.05477107402652974,
      "grad_norm": 0.37231582403182983,
      "learning_rate": 0.000105541147491597,
      "loss": 0.9618,
      "step": 112
    },
    {
      "epoch": 0.05526010147319518,
      "grad_norm": 0.44430795311927795,
      "learning_rate": 0.00010369514993891452,
      "loss": 0.9858,
      "step": 113
    },
    {
      "epoch": 0.05574912891986063,
      "grad_norm": 0.3270968794822693,
      "learning_rate": 0.00010184789049591299,
      "loss": 1.0593,
      "step": 114
    },
    {
      "epoch": 0.05623815636652607,
      "grad_norm": 0.5233888626098633,
      "learning_rate": 0.0001,
      "loss": 1.1894,
      "step": 115
    },
    {
      "epoch": 0.056727183813191515,
      "grad_norm": 0.27441027760505676,
      "learning_rate": 9.815210950408704e-05,
      "loss": 1.1149,
      "step": 116
    },
    {
      "epoch": 0.05721621125985696,
      "grad_norm": 0.31127995252609253,
      "learning_rate": 9.630485006108553e-05,
      "loss": 0.9754,
      "step": 117
    },
    {
      "epoch": 0.0577052387065224,
      "grad_norm": 0.2927124798297882,
      "learning_rate": 9.4458852508403e-05,
      "loss": 1.1016,
      "step": 118
    },
    {
      "epoch": 0.058194266153187846,
      "grad_norm": 0.2648122012615204,
      "learning_rate": 9.261474725251261e-05,
      "loss": 1.1289,
      "step": 119
    },
    {
      "epoch": 0.05868329359985329,
      "grad_norm": 0.543241560459137,
      "learning_rate": 9.077316405366981e-05,
      "loss": 1.0567,
      "step": 120
    },
    {
      "epoch": 0.05917232104651873,
      "grad_norm": 0.49946677684783936,
      "learning_rate": 8.893473181084994e-05,
      "loss": 1.1589,
      "step": 121
    },
    {
      "epoch": 0.05966134849318418,
      "grad_norm": 0.4257027506828308,
      "learning_rate": 8.710007834697969e-05,
      "loss": 1.042,
      "step": 122
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 0.31747233867645264,
      "learning_rate": 8.526983019453623e-05,
      "loss": 1.1559,
      "step": 123
    },
    {
      "epoch": 0.06063940338651507,
      "grad_norm": 0.3513385057449341,
      "learning_rate": 8.344461238158699e-05,
      "loss": 1.0482,
      "step": 124
    },
    {
      "epoch": 0.061128430833180515,
      "grad_norm": 0.2956028878688812,
      "learning_rate": 8.162504821834295e-05,
      "loss": 1.115,
      "step": 125
    },
    {
      "epoch": 0.06161745827984596,
      "grad_norm": 0.3449247479438782,
      "learning_rate": 7.9811759084299e-05,
      "loss": 1.1518,
      "step": 126
    },
    {
      "epoch": 0.0621064857265114,
      "grad_norm": 0.3520428538322449,
      "learning_rate": 7.800536421603317e-05,
      "loss": 1.1952,
      "step": 127
    },
    {
      "epoch": 0.06259551317317684,
      "grad_norm": 0.43081384897232056,
      "learning_rate": 7.620648049573815e-05,
      "loss": 1.0866,
      "step": 128
    },
    {
      "epoch": 0.06308454061984228,
      "grad_norm": 0.31005534529685974,
      "learning_rate": 7.441572224055644e-05,
      "loss": 1.1529,
      "step": 129
    },
    {
      "epoch": 0.06357356806650773,
      "grad_norm": 0.2653469145298004,
      "learning_rate": 7.263370099279172e-05,
      "loss": 1.0994,
      "step": 130
    },
    {
      "epoch": 0.06406259551317317,
      "grad_norm": 0.42570021748542786,
      "learning_rate": 7.086102531106754e-05,
      "loss": 1.1398,
      "step": 131
    },
    {
      "epoch": 0.06455162295983861,
      "grad_norm": 0.30308008193969727,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.0925,
      "step": 132
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 0.35984402894973755,
      "learning_rate": 6.734612871599168e-05,
      "loss": 1.1588,
      "step": 133
    },
    {
      "epoch": 0.06552967785316952,
      "grad_norm": 0.3182411789894104,
      "learning_rate": 6.560510813660719e-05,
      "loss": 1.0635,
      "step": 134
    },
    {
      "epoch": 0.06601870529983496,
      "grad_norm": 0.34441515803337097,
      "learning_rate": 6.387583338128471e-05,
      "loss": 1.3016,
      "step": 135
    },
    {
      "epoch": 0.0665077327465004,
      "grad_norm": 0.3226831555366516,
      "learning_rate": 6.215889499576898e-05,
      "loss": 1.1228,
      "step": 136
    },
    {
      "epoch": 0.0665077327465004,
      "eval_loss": 1.0842134952545166,
      "eval_runtime": 758.6566,
      "eval_samples_per_second": 3.405,
      "eval_steps_per_second": 1.135,
      "step": 136
    },
    {
      "epoch": 0.06699676019316585,
      "grad_norm": 0.2443569004535675,
      "learning_rate": 6.0454879312945754e-05,
      "loss": 1.02,
      "step": 137
    },
    {
      "epoch": 0.06748578763983129,
      "grad_norm": 0.29934799671173096,
      "learning_rate": 5.876436825260967e-05,
      "loss": 1.094,
      "step": 138
    },
    {
      "epoch": 0.06797481508649673,
      "grad_norm": 0.5698016881942749,
      "learning_rate": 5.708793912273911e-05,
      "loss": 0.7654,
      "step": 139
    },
    {
      "epoch": 0.06846384253316218,
      "grad_norm": 0.4488852322101593,
      "learning_rate": 5.542616442234618e-05,
      "loss": 1.2071,
      "step": 140
    },
    {
      "epoch": 0.06895286997982762,
      "grad_norm": 0.3017083406448364,
      "learning_rate": 5.37796116459687e-05,
      "loss": 0.8955,
      "step": 141
    },
    {
      "epoch": 0.06944189742649307,
      "grad_norm": 0.47689270973205566,
      "learning_rate": 5.214884308987136e-05,
      "loss": 0.9691,
      "step": 142
    },
    {
      "epoch": 0.06993092487315851,
      "grad_norm": 0.2770170569419861,
      "learning_rate": 5.0534415660022136e-05,
      "loss": 1.0761,
      "step": 143
    },
    {
      "epoch": 0.07041995231982395,
      "grad_norm": 0.24565915763378143,
      "learning_rate": 4.893688068190932e-05,
      "loss": 1.1392,
      "step": 144
    },
    {
      "epoch": 0.0709089797664894,
      "grad_norm": 0.4684452414512634,
      "learning_rate": 4.735678371226441e-05,
      "loss": 0.9979,
      "step": 145
    },
    {
      "epoch": 0.07139800721315484,
      "grad_norm": 0.35415977239608765,
      "learning_rate": 4.5794664352755055e-05,
      "loss": 1.1084,
      "step": 146
    },
    {
      "epoch": 0.07188703465982028,
      "grad_norm": 0.2728458344936371,
      "learning_rate": 4.425105606571145e-05,
      "loss": 1.0808,
      "step": 147
    },
    {
      "epoch": 0.07237606210648573,
      "grad_norm": 0.26373422145843506,
      "learning_rate": 4.272648599194948e-05,
      "loss": 1.0824,
      "step": 148
    },
    {
      "epoch": 0.07286508955315117,
      "grad_norm": 0.3004222512245178,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.091,
      "step": 149
    },
    {
      "epoch": 0.07335411699981662,
      "grad_norm": 0.2643493413925171,
      "learning_rate": 3.973653636207437e-05,
      "loss": 1.0998,
      "step": 150
    },
    {
      "epoch": 0.07384314444648206,
      "grad_norm": 0.326731413602829,
      "learning_rate": 3.8272177871020723e-05,
      "loss": 1.0994,
      "step": 151
    },
    {
      "epoch": 0.0743321718931475,
      "grad_norm": 0.3203975260257721,
      "learning_rate": 3.682889937467493e-05,
      "loss": 0.9946,
      "step": 152
    },
    {
      "epoch": 0.07482119933981295,
      "grad_norm": 0.38719937205314636,
      "learning_rate": 3.540719375132129e-05,
      "loss": 0.986,
      "step": 153
    },
    {
      "epoch": 0.07531022678647839,
      "grad_norm": 0.5814553499221802,
      "learning_rate": 3.400754651212776e-05,
      "loss": 1.063,
      "step": 154
    },
    {
      "epoch": 0.07579925423314383,
      "grad_norm": 0.3577742278575897,
      "learning_rate": 3.263043563534428e-05,
      "loss": 1.1242,
      "step": 155
    },
    {
      "epoch": 0.07628828167980928,
      "grad_norm": 0.36914464831352234,
      "learning_rate": 3.1276331403073735e-05,
      "loss": 1.0626,
      "step": 156
    },
    {
      "epoch": 0.07677730912647472,
      "grad_norm": 0.40453627705574036,
      "learning_rate": 2.9945696240670906e-05,
      "loss": 1.1679,
      "step": 157
    },
    {
      "epoch": 0.07726633657314017,
      "grad_norm": 0.2733079195022583,
      "learning_rate": 2.8638984558824777e-05,
      "loss": 1.0582,
      "step": 158
    },
    {
      "epoch": 0.07775536401980561,
      "grad_norm": 0.30982354283332825,
      "learning_rate": 2.7356642598377603e-05,
      "loss": 1.0806,
      "step": 159
    },
    {
      "epoch": 0.07824439146647105,
      "grad_norm": 0.20342323184013367,
      "learning_rate": 2.6099108277934103e-05,
      "loss": 1.0705,
      "step": 160
    },
    {
      "epoch": 0.0787334189131365,
      "grad_norm": 0.3492101728916168,
      "learning_rate": 2.4866811044312665e-05,
      "loss": 1.2527,
      "step": 161
    },
    {
      "epoch": 0.07922244635980194,
      "grad_norm": 0.35257744789123535,
      "learning_rate": 2.36601717258897e-05,
      "loss": 0.9998,
      "step": 162
    },
    {
      "epoch": 0.07971147380646738,
      "grad_norm": 0.3167296350002289,
      "learning_rate": 2.2479602388887012e-05,
      "loss": 0.9807,
      "step": 163
    },
    {
      "epoch": 0.08020050125313283,
      "grad_norm": 0.33515843749046326,
      "learning_rate": 2.132550619665168e-05,
      "loss": 0.9058,
      "step": 164
    },
    {
      "epoch": 0.08068952869979827,
      "grad_norm": 0.29648372530937195,
      "learning_rate": 2.0198277271976052e-05,
      "loss": 1.1151,
      "step": 165
    },
    {
      "epoch": 0.08117855614646372,
      "grad_norm": 0.4363006353378296,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.9493,
      "step": 166
    },
    {
      "epoch": 0.08166758359312916,
      "grad_norm": 0.3400018811225891,
      "learning_rate": 1.8025951709277898e-05,
      "loss": 1.1108,
      "step": 167
    },
    {
      "epoch": 0.0821566110397946,
      "grad_norm": 0.31908851861953735,
      "learning_rate": 1.6981596918444953e-05,
      "loss": 1.2405,
      "step": 168
    },
    {
      "epoch": 0.08264563848646005,
      "grad_norm": 0.33976632356643677,
      "learning_rate": 1.5965592836210743e-05,
      "loss": 1.0869,
      "step": 169
    },
    {
      "epoch": 0.08313466593312549,
      "grad_norm": 0.3594518303871155,
      "learning_rate": 1.4978286427038601e-05,
      "loss": 0.9368,
      "step": 170
    },
    {
      "epoch": 0.08313466593312549,
      "eval_loss": 1.0824781656265259,
      "eval_runtime": 759.1264,
      "eval_samples_per_second": 3.403,
      "eval_steps_per_second": 1.134,
      "step": 170
    },
    {
      "epoch": 0.08362369337979095,
      "grad_norm": 0.4409734010696411,
      "learning_rate": 1.4020014855162755e-05,
      "loss": 1.1906,
      "step": 171
    },
    {
      "epoch": 0.08411272082645639,
      "grad_norm": 0.28618118166923523,
      "learning_rate": 1.3091105369447165e-05,
      "loss": 0.9954,
      "step": 172
    },
    {
      "epoch": 0.08460174827312184,
      "grad_norm": 0.33469173312187195,
      "learning_rate": 1.2191875191630209e-05,
      "loss": 1.1603,
      "step": 173
    },
    {
      "epoch": 0.08509077571978728,
      "grad_norm": 0.2905137240886688,
      "learning_rate": 1.1322631407993811e-05,
      "loss": 1.0418,
      "step": 174
    },
    {
      "epoch": 0.08557980316645272,
      "grad_norm": 0.25632575154304504,
      "learning_rate": 1.0483670864493778e-05,
      "loss": 1.0092,
      "step": 175
    },
    {
      "epoch": 0.08606883061311817,
      "grad_norm": 0.4478399157524109,
      "learning_rate": 9.675280065387116e-06,
      "loss": 1.0666,
      "step": 176
    },
    {
      "epoch": 0.08655785805978361,
      "grad_norm": 0.2583039104938507,
      "learning_rate": 8.897735075391155e-06,
      "loss": 0.8946,
      "step": 177
    },
    {
      "epoch": 0.08704688550644905,
      "grad_norm": 0.30150678753852844,
      "learning_rate": 8.151301425407699e-06,
      "loss": 1.0711,
      "step": 178
    },
    {
      "epoch": 0.0875359129531145,
      "grad_norm": 0.2433328628540039,
      "learning_rate": 7.43623402184438e-06,
      "loss": 0.9163,
      "step": 179
    },
    {
      "epoch": 0.08802494039977994,
      "grad_norm": 0.42990484833717346,
      "learning_rate": 6.75277705956443e-06,
      "loss": 1.0391,
      "step": 180
    },
    {
      "epoch": 0.08851396784644538,
      "grad_norm": 0.30807220935821533,
      "learning_rate": 6.1011639384943585e-06,
      "loss": 1.1392,
      "step": 181
    },
    {
      "epoch": 0.08900299529311083,
      "grad_norm": 0.26109498739242554,
      "learning_rate": 5.481617183918053e-06,
      "loss": 1.1042,
      "step": 182
    },
    {
      "epoch": 0.08949202273977627,
      "grad_norm": 0.35243722796440125,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 1.009,
      "step": 183
    },
    {
      "epoch": 0.08998105018644172,
      "grad_norm": 0.3016376495361328,
      "learning_rate": 4.339558049955927e-06,
      "loss": 1.161,
      "step": 184
    },
    {
      "epoch": 0.09047007763310716,
      "grad_norm": 0.28883588314056396,
      "learning_rate": 3.817435682718096e-06,
      "loss": 1.0669,
      "step": 185
    },
    {
      "epoch": 0.0909591050797726,
      "grad_norm": 0.2308908998966217,
      "learning_rate": 3.3281595730812575e-06,
      "loss": 1.0341,
      "step": 186
    },
    {
      "epoch": 0.09144813252643805,
      "grad_norm": 0.28636959195137024,
      "learning_rate": 2.8718968083886075e-06,
      "loss": 1.2459,
      "step": 187
    },
    {
      "epoch": 0.09193715997310349,
      "grad_norm": 0.2441776990890503,
      "learning_rate": 2.4488032019563402e-06,
      "loss": 1.0977,
      "step": 188
    },
    {
      "epoch": 0.09242618741976893,
      "grad_norm": 0.4734705686569214,
      "learning_rate": 2.0590232398634114e-06,
      "loss": 1.0091,
      "step": 189
    },
    {
      "epoch": 0.09291521486643438,
      "grad_norm": 0.32178983092308044,
      "learning_rate": 1.7026900316098215e-06,
      "loss": 1.1748,
      "step": 190
    },
    {
      "epoch": 0.09340424231309982,
      "grad_norm": 0.2973954677581787,
      "learning_rate": 1.3799252646597426e-06,
      "loss": 1.2553,
      "step": 191
    },
    {
      "epoch": 0.09389326975976527,
      "grad_norm": 0.30735060572624207,
      "learning_rate": 1.0908391628854041e-06,
      "loss": 1.0603,
      "step": 192
    },
    {
      "epoch": 0.09438229720643071,
      "grad_norm": 0.39257532358169556,
      "learning_rate": 8.355304489257254e-07,
      "loss": 1.0304,
      "step": 193
    },
    {
      "epoch": 0.09487132465309615,
      "grad_norm": 0.31010863184928894,
      "learning_rate": 6.140863104726391e-07,
      "loss": 1.0806,
      "step": 194
    },
    {
      "epoch": 0.0953603520997616,
      "grad_norm": 0.2375696897506714,
      "learning_rate": 4.2658237049655323e-07,
      "loss": 1.1009,
      "step": 195
    },
    {
      "epoch": 0.09584937954642704,
      "grad_norm": 0.4178907871246338,
      "learning_rate": 2.7308266142119785e-07,
      "loss": 1.0427,
      "step": 196
    },
    {
      "epoch": 0.09633840699309248,
      "grad_norm": 0.26013046503067017,
      "learning_rate": 1.5363960325660565e-07,
      "loss": 1.2129,
      "step": 197
    },
    {
      "epoch": 0.09682743443975793,
      "grad_norm": 0.41328510642051697,
      "learning_rate": 6.829398569770939e-08,
      "loss": 1.0907,
      "step": 198
    },
    {
      "epoch": 0.09731646188642337,
      "grad_norm": 0.354490727186203,
      "learning_rate": 1.7074954194729044e-08,
      "loss": 1.1142,
      "step": 199
    },
    {
      "epoch": 0.09780548933308882,
      "grad_norm": 0.43180105090141296,
      "learning_rate": 0.0,
      "loss": 1.0926,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.33947061927936e+17,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}