{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.025437201907790145,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001271860095389507,
      "grad_norm": 1.9835193157196045,
      "learning_rate": 2e-05,
      "loss": 5.4485,
      "step": 1
    },
    {
      "epoch": 0.0001271860095389507,
      "eval_loss": 1.2489664554595947,
      "eval_runtime": 60.2564,
      "eval_samples_per_second": 54.949,
      "eval_steps_per_second": 27.483,
      "step": 1
    },
    {
      "epoch": 0.0002543720190779014,
      "grad_norm": 1.839722990989685,
      "learning_rate": 4e-05,
      "loss": 5.0062,
      "step": 2
    },
    {
      "epoch": 0.00038155802861685216,
      "grad_norm": 1.906867265701294,
      "learning_rate": 6e-05,
      "loss": 5.0884,
      "step": 3
    },
    {
      "epoch": 0.0005087440381558028,
      "grad_norm": 1.7935138940811157,
      "learning_rate": 8e-05,
      "loss": 4.9646,
      "step": 4
    },
    {
      "epoch": 0.0006359300476947536,
      "grad_norm": 2.1912240982055664,
      "learning_rate": 0.0001,
      "loss": 5.574,
      "step": 5
    },
    {
      "epoch": 0.0007631160572337043,
      "grad_norm": 1.704566478729248,
      "learning_rate": 0.00012,
      "loss": 4.7769,
      "step": 6
    },
    {
      "epoch": 0.000890302066772655,
      "grad_norm": 1.8012601137161255,
      "learning_rate": 0.00014,
      "loss": 4.937,
      "step": 7
    },
    {
      "epoch": 0.0010174880763116057,
      "grad_norm": 1.76153564453125,
      "learning_rate": 0.00016,
      "loss": 4.7734,
      "step": 8
    },
    {
      "epoch": 0.0011446740858505565,
      "grad_norm": 1.877334713935852,
      "learning_rate": 0.00018,
      "loss": 4.9324,
      "step": 9
    },
    {
      "epoch": 0.0012718600953895071,
      "grad_norm": 1.7994229793548584,
      "learning_rate": 0.0002,
      "loss": 4.6046,
      "step": 10
    },
    {
      "epoch": 0.0013990461049284578,
      "grad_norm": 1.9988417625427246,
      "learning_rate": 0.0001999863304992469,
      "loss": 4.3125,
      "step": 11
    },
    {
      "epoch": 0.0015262321144674086,
      "grad_norm": 2.3464603424072266,
      "learning_rate": 0.00019994532573409262,
      "loss": 4.363,
      "step": 12
    },
    {
      "epoch": 0.0016534181240063592,
      "grad_norm": 2.255720615386963,
      "learning_rate": 0.00019987699691483048,
      "loss": 4.1383,
      "step": 13
    },
    {
      "epoch": 0.00178060413354531,
      "grad_norm": 2.2891433238983154,
      "learning_rate": 0.00019978136272187747,
      "loss": 4.1131,
      "step": 14
    },
    {
      "epoch": 0.0019077901430842607,
      "grad_norm": 2.1453323364257812,
      "learning_rate": 0.000199658449300667,
      "loss": 4.1299,
      "step": 15
    },
    {
      "epoch": 0.0020349761526232114,
      "grad_norm": 1.9900203943252563,
      "learning_rate": 0.00019950829025450114,
      "loss": 4.0106,
      "step": 16
    },
    {
      "epoch": 0.002162162162162162,
      "grad_norm": 1.8799800872802734,
      "learning_rate": 0.00019933092663536382,
      "loss": 4.0144,
      "step": 17
    },
    {
      "epoch": 0.002289348171701113,
      "grad_norm": 2.0695888996124268,
      "learning_rate": 0.00019912640693269752,
      "loss": 3.7752,
      "step": 18
    },
    {
      "epoch": 0.0024165341812400635,
      "grad_norm": 2.120725631713867,
      "learning_rate": 0.00019889478706014687,
      "loss": 4.0842,
      "step": 19
    },
    {
      "epoch": 0.0025437201907790143,
      "grad_norm": 2.8703718185424805,
      "learning_rate": 0.00019863613034027224,
      "loss": 3.6905,
      "step": 20
    },
    {
      "epoch": 0.002670906200317965,
      "grad_norm": 1.7893959283828735,
      "learning_rate": 0.00019835050748723824,
      "loss": 3.5627,
      "step": 21
    },
    {
      "epoch": 0.0027980922098569156,
      "grad_norm": 1.9003410339355469,
      "learning_rate": 0.00019803799658748094,
      "loss": 3.6049,
      "step": 22
    },
    {
      "epoch": 0.0029252782193958664,
      "grad_norm": 2.649674892425537,
      "learning_rate": 0.00019769868307835994,
      "loss": 3.7806,
      "step": 23
    },
    {
      "epoch": 0.0030524642289348172,
      "grad_norm": 1.8168840408325195,
      "learning_rate": 0.0001973326597248006,
      "loss": 3.4188,
      "step": 24
    },
    {
      "epoch": 0.003179650238473768,
      "grad_norm": 1.8296242952346802,
      "learning_rate": 0.00019694002659393305,
      "loss": 3.6451,
      "step": 25
    },
    {
      "epoch": 0.0033068362480127185,
      "grad_norm": 1.8689442873001099,
      "learning_rate": 0.00019652089102773488,
      "loss": 3.5423,
      "step": 26
    },
    {
      "epoch": 0.0034340222575516693,
      "grad_norm": 1.7191494703292847,
      "learning_rate": 0.00019607536761368484,
      "loss": 3.5463,
      "step": 27
    },
    {
      "epoch": 0.00356120826709062,
      "grad_norm": 1.8769090175628662,
      "learning_rate": 0.00019560357815343577,
      "loss": 3.6548,
      "step": 28
    },
    {
      "epoch": 0.0036883942766295706,
      "grad_norm": 1.6859794855117798,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.3713,
      "step": 29
    },
    {
      "epoch": 0.0038155802861685214,
      "grad_norm": 1.5716698169708252,
      "learning_rate": 0.00019458172417006347,
      "loss": 3.2842,
      "step": 30
    },
    {
      "epoch": 0.003942766295707472,
      "grad_norm": 1.8034677505493164,
      "learning_rate": 0.00019403193901161613,
      "loss": 3.533,
      "step": 31
    },
    {
      "epoch": 0.004069952305246423,
      "grad_norm": 1.8093938827514648,
      "learning_rate": 0.0001934564464599461,
      "loss": 3.408,
      "step": 32
    },
    {
      "epoch": 0.0041971383147853735,
      "grad_norm": 1.7909035682678223,
      "learning_rate": 0.00019285540384897073,
      "loss": 3.2401,
      "step": 33
    },
    {
      "epoch": 0.004324324324324324,
      "grad_norm": 1.7447187900543213,
      "learning_rate": 0.00019222897549773848,
      "loss": 3.2696,
      "step": 34
    },
    {
      "epoch": 0.004451510333863275,
      "grad_norm": 1.5972126722335815,
      "learning_rate": 0.00019157733266550575,
      "loss": 3.0369,
      "step": 35
    },
    {
      "epoch": 0.004578696343402226,
      "grad_norm": 1.729097843170166,
      "learning_rate": 0.00019090065350491626,
      "loss": 3.2384,
      "step": 36
    },
    {
      "epoch": 0.004705882352941176,
      "grad_norm": 1.8049160242080688,
      "learning_rate": 0.00019019912301329592,
      "loss": 3.2673,
      "step": 37
    },
    {
      "epoch": 0.004833068362480127,
      "grad_norm": 1.684900164604187,
      "learning_rate": 0.00018947293298207635,
      "loss": 3.3017,
      "step": 38
    },
    {
      "epoch": 0.004960254372019078,
      "grad_norm": 2.184971332550049,
      "learning_rate": 0.0001887222819443612,
      "loss": 2.946,
      "step": 39
    },
    {
      "epoch": 0.005087440381558029,
      "grad_norm": 1.815535306930542,
      "learning_rate": 0.0001879473751206489,
      "loss": 3.0601,
      "step": 40
    },
    {
      "epoch": 0.0052146263910969794,
      "grad_norm": 1.8295841217041016,
      "learning_rate": 0.00018714842436272773,
      "loss": 3.2226,
      "step": 41
    },
    {
      "epoch": 0.00534181240063593,
      "grad_norm": 1.9899147748947144,
      "learning_rate": 0.00018632564809575742,
      "loss": 3.225,
      "step": 42
    },
    {
      "epoch": 0.005468998410174881,
      "grad_norm": 2.021754026412964,
      "learning_rate": 0.0001854792712585539,
      "loss": 3.0691,
      "step": 43
    },
    {
      "epoch": 0.005596184419713831,
      "grad_norm": 1.8898154497146606,
      "learning_rate": 0.00018460952524209355,
      "loss": 3.2772,
      "step": 44
    },
    {
      "epoch": 0.005723370429252782,
      "grad_norm": 2.083461046218872,
      "learning_rate": 0.00018371664782625287,
      "loss": 3.4458,
      "step": 45
    },
    {
      "epoch": 0.005850556438791733,
      "grad_norm": 2.219532012939453,
      "learning_rate": 0.00018280088311480201,
      "loss": 3.3751,
      "step": 46
    },
    {
      "epoch": 0.005977742448330684,
      "grad_norm": 2.285486936569214,
      "learning_rate": 0.00018186248146866927,
      "loss": 3.3656,
      "step": 47
    },
    {
      "epoch": 0.0061049284578696345,
      "grad_norm": 2.1301989555358887,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.9066,
      "step": 48
    },
    {
      "epoch": 0.006232114467408585,
      "grad_norm": 2.079562187194824,
      "learning_rate": 0.0001799187996894925,
      "loss": 3.0637,
      "step": 49
    },
    {
      "epoch": 0.006359300476947536,
      "grad_norm": 2.057091236114502,
      "learning_rate": 0.00017891405093963938,
      "loss": 3.1446,
      "step": 50
    },
    {
      "epoch": 0.006359300476947536,
      "eval_loss": 0.7800452709197998,
      "eval_runtime": 57.7119,
      "eval_samples_per_second": 57.371,
      "eval_steps_per_second": 28.694,
      "step": 50
    },
    {
      "epoch": 0.006486486486486486,
      "grad_norm": 1.9653096199035645,
      "learning_rate": 0.00017788772787621126,
      "loss": 3.393,
      "step": 51
    },
    {
      "epoch": 0.006613672496025437,
      "grad_norm": 1.9508553743362427,
      "learning_rate": 0.00017684011108568592,
      "loss": 3.1593,
      "step": 52
    },
    {
      "epoch": 0.006740858505564388,
      "grad_norm": 1.9427250623703003,
      "learning_rate": 0.0001757714869760335,
      "loss": 3.3619,
      "step": 53
    },
    {
      "epoch": 0.006868044515103339,
      "grad_norm": 1.902197241783142,
      "learning_rate": 0.0001746821476984154,
      "loss": 3.1835,
      "step": 54
    },
    {
      "epoch": 0.0069952305246422895,
      "grad_norm": 2.077125310897827,
      "learning_rate": 0.00017357239106731317,
      "loss": 3.4491,
      "step": 55
    },
    {
      "epoch": 0.00712241653418124,
      "grad_norm": 1.8819434642791748,
      "learning_rate": 0.00017244252047910892,
      "loss": 3.0944,
      "step": 56
    },
    {
      "epoch": 0.00724960254372019,
      "grad_norm": 2.3512206077575684,
      "learning_rate": 0.00017129284482913972,
      "loss": 3.1957,
      "step": 57
    },
    {
      "epoch": 0.007376788553259141,
      "grad_norm": 2.125260829925537,
      "learning_rate": 0.00017012367842724887,
      "loss": 2.8759,
      "step": 58
    },
    {
      "epoch": 0.007503974562798092,
      "grad_norm": 2.0126636028289795,
      "learning_rate": 0.0001689353409118566,
      "loss": 3.2306,
      "step": 59
    },
    {
      "epoch": 0.007631160572337043,
      "grad_norm": 2.0234174728393555,
      "learning_rate": 0.00016772815716257412,
      "loss": 3.1808,
      "step": 60
    },
    {
      "epoch": 0.007758346581875994,
      "grad_norm": 2.0953781604766846,
      "learning_rate": 0.0001665024572113848,
      "loss": 3.0547,
      "step": 61
    },
    {
      "epoch": 0.007885532591414944,
      "grad_norm": 2.0005664825439453,
      "learning_rate": 0.00016525857615241687,
      "loss": 3.1831,
      "step": 62
    },
    {
      "epoch": 0.008012718600953895,
      "grad_norm": 2.023897886276245,
      "learning_rate": 0.00016399685405033167,
      "loss": 3.0127,
      "step": 63
    },
    {
      "epoch": 0.008139904610492845,
      "grad_norm": 2.0961215496063232,
      "learning_rate": 0.0001627176358473537,
      "loss": 3.3373,
      "step": 64
    },
    {
      "epoch": 0.008267090620031796,
      "grad_norm": 2.068119525909424,
      "learning_rate": 0.0001614212712689668,
      "loss": 3.2092,
      "step": 65
    },
    {
      "epoch": 0.008394276629570747,
      "grad_norm": 2.0452160835266113,
      "learning_rate": 0.00016010811472830252,
      "loss": 3.2085,
      "step": 66
    },
    {
      "epoch": 0.008521462639109698,
      "grad_norm": 2.156864643096924,
      "learning_rate": 0.00015877852522924732,
      "loss": 3.0868,
      "step": 67
    },
    {
      "epoch": 0.008648648648648649,
      "grad_norm": 2.029207706451416,
      "learning_rate": 0.00015743286626829437,
      "loss": 2.9679,
      "step": 68
    },
    {
      "epoch": 0.0087758346581876,
      "grad_norm": 2.12054181098938,
      "learning_rate": 0.0001560715057351673,
      "loss": 3.1446,
      "step": 69
    },
    {
      "epoch": 0.00890302066772655,
      "grad_norm": 2.1028153896331787,
      "learning_rate": 0.00015469481581224272,
      "loss": 3.0386,
      "step": 70
    },
    {
      "epoch": 0.009030206677265501,
      "grad_norm": 2.2078723907470703,
      "learning_rate": 0.0001533031728727994,
      "loss": 3.2846,
      "step": 71
    },
    {
      "epoch": 0.009157392686804452,
      "grad_norm": 2.080521821975708,
      "learning_rate": 0.00015189695737812152,
      "loss": 3.046,
      "step": 72
    },
    {
      "epoch": 0.009284578696343403,
      "grad_norm": 2.0975699424743652,
      "learning_rate": 0.0001504765537734844,
      "loss": 2.8228,
      "step": 73
    },
    {
      "epoch": 0.009411764705882352,
      "grad_norm": 2.443129062652588,
      "learning_rate": 0.00014904235038305083,
      "loss": 3.1119,
      "step": 74
    },
    {
      "epoch": 0.009538950715421303,
      "grad_norm": 2.1817243099212646,
      "learning_rate": 0.00014759473930370736,
      "loss": 2.6607,
      "step": 75
    },
    {
      "epoch": 0.009666136724960254,
      "grad_norm": 2.2016985416412354,
      "learning_rate": 0.0001461341162978688,
      "loss": 2.9715,
      "step": 76
    },
    {
      "epoch": 0.009793322734499205,
      "grad_norm": 2.2988955974578857,
      "learning_rate": 0.00014466088068528068,
      "loss": 2.962,
      "step": 77
    },
    {
      "epoch": 0.009920508744038155,
      "grad_norm": 2.2614760398864746,
      "learning_rate": 0.00014317543523384928,
      "loss": 3.1009,
      "step": 78
    },
    {
      "epoch": 0.010047694753577106,
      "grad_norm": 2.051297664642334,
      "learning_rate": 0.00014167818604952906,
      "loss": 3.0087,
      "step": 79
    },
    {
      "epoch": 0.010174880763116057,
      "grad_norm": 2.0947837829589844,
      "learning_rate": 0.00014016954246529696,
      "loss": 3.0739,
      "step": 80
    },
    {
      "epoch": 0.010302066772655008,
      "grad_norm": 2.4646780490875244,
      "learning_rate": 0.00013864991692924523,
      "loss": 3.2066,
      "step": 81
    },
    {
      "epoch": 0.010429252782193959,
      "grad_norm": 2.156864881515503,
      "learning_rate": 0.00013711972489182208,
      "loss": 3.2273,
      "step": 82
    },
    {
      "epoch": 0.01055643879173291,
      "grad_norm": 2.163877010345459,
      "learning_rate": 0.00013557938469225167,
      "loss": 3.2036,
      "step": 83
    },
    {
      "epoch": 0.01068362480127186,
      "grad_norm": 2.1124367713928223,
      "learning_rate": 0.00013402931744416433,
      "loss": 2.9042,
      "step": 84
    },
    {
      "epoch": 0.010810810810810811,
      "grad_norm": 2.2118308544158936,
      "learning_rate": 0.00013246994692046836,
      "loss": 3.2564,
      "step": 85
    },
    {
      "epoch": 0.010937996820349762,
      "grad_norm": 2.289252758026123,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.05,
      "step": 86
    },
    {
      "epoch": 0.011065182829888713,
      "grad_norm": 2.044328451156616,
      "learning_rate": 0.0001293250037384465,
      "loss": 2.8559,
      "step": 87
    },
    {
      "epoch": 0.011192368839427662,
      "grad_norm": 2.127413511276245,
      "learning_rate": 0.00012774029087618446,
      "loss": 3.0749,
      "step": 88
    },
    {
      "epoch": 0.011319554848966613,
      "grad_norm": 2.1147000789642334,
      "learning_rate": 0.00012614799409538198,
      "loss": 3.065,
      "step": 89
    },
    {
      "epoch": 0.011446740858505564,
      "grad_norm": 2.2932112216949463,
      "learning_rate": 0.00012454854871407994,
      "loss": 3.6366,
      "step": 90
    },
    {
      "epoch": 0.011573926868044515,
      "grad_norm": 2.405611753463745,
      "learning_rate": 0.00012294239200467516,
      "loss": 3.1775,
      "step": 91
    },
    {
      "epoch": 0.011701112877583466,
      "grad_norm": 2.0750105381011963,
      "learning_rate": 0.0001213299630743747,
      "loss": 2.9886,
      "step": 92
    },
    {
      "epoch": 0.011828298887122416,
      "grad_norm": 2.072420358657837,
      "learning_rate": 0.00011971170274514802,
      "loss": 3.0914,
      "step": 93
    },
    {
      "epoch": 0.011955484896661367,
      "grad_norm": 2.19963002204895,
      "learning_rate": 0.000118088053433211,
      "loss": 2.9166,
      "step": 94
    },
    {
      "epoch": 0.012082670906200318,
      "grad_norm": 2.1508893966674805,
      "learning_rate": 0.00011645945902807341,
      "loss": 2.8944,
      "step": 95
    },
    {
      "epoch": 0.012209856915739269,
      "grad_norm": 2.4836275577545166,
      "learning_rate": 0.0001148263647711842,
      "loss": 2.9622,
      "step": 96
    },
    {
      "epoch": 0.01233704292527822,
      "grad_norm": 2.2222437858581543,
      "learning_rate": 0.00011318921713420691,
      "loss": 2.8688,
      "step": 97
    },
    {
      "epoch": 0.01246422893481717,
      "grad_norm": 2.1132421493530273,
      "learning_rate": 0.00011154846369695863,
      "loss": 2.8259,
      "step": 98
    },
    {
      "epoch": 0.012591414944356122,
      "grad_norm": 2.1007161140441895,
      "learning_rate": 0.0001099045530250463,
      "loss": 2.7156,
      "step": 99
    },
    {
      "epoch": 0.012718600953895072,
      "grad_norm": 2.1596603393554688,
      "learning_rate": 0.00010825793454723325,
      "loss": 3.0597,
      "step": 100
    },
    {
      "epoch": 0.012718600953895072,
      "eval_loss": 0.7423936724662781,
      "eval_runtime": 57.8996,
      "eval_samples_per_second": 57.185,
      "eval_steps_per_second": 28.601,
      "step": 100
    },
    {
      "epoch": 0.012845786963434021,
      "grad_norm": 2.3275163173675537,
      "learning_rate": 0.00010660905843256994,
      "loss": 3.1327,
      "step": 101
    },
    {
      "epoch": 0.012972972972972972,
      "grad_norm": 2.0324950218200684,
      "learning_rate": 0.00010495837546732224,
      "loss": 2.7223,
      "step": 102
    },
    {
      "epoch": 0.013100158982511923,
      "grad_norm": 2.420083999633789,
      "learning_rate": 0.00010330633693173082,
      "loss": 3.1192,
      "step": 103
    },
    {
      "epoch": 0.013227344992050874,
      "grad_norm": 2.116345167160034,
      "learning_rate": 0.00010165339447663587,
      "loss": 3.1318,
      "step": 104
    },
    {
      "epoch": 0.013354531001589825,
      "grad_norm": 2.523977756500244,
      "learning_rate": 0.0001,
      "loss": 2.8798,
      "step": 105
    },
    {
      "epoch": 0.013481717011128776,
      "grad_norm": 2.141871213912964,
      "learning_rate": 9.834660552336415e-05,
      "loss": 3.1058,
      "step": 106
    },
    {
      "epoch": 0.013608903020667727,
      "grad_norm": 2.2081823348999023,
      "learning_rate": 9.669366306826919e-05,
      "loss": 2.9769,
      "step": 107
    },
    {
      "epoch": 0.013736089030206677,
      "grad_norm": 2.0940332412719727,
      "learning_rate": 9.504162453267777e-05,
      "loss": 2.9284,
      "step": 108
    },
    {
      "epoch": 0.013863275039745628,
      "grad_norm": 2.2576355934143066,
      "learning_rate": 9.339094156743007e-05,
      "loss": 3.0978,
      "step": 109
    },
    {
      "epoch": 0.013990461049284579,
      "grad_norm": 2.107511043548584,
      "learning_rate": 9.174206545276677e-05,
      "loss": 2.8895,
      "step": 110
    },
    {
      "epoch": 0.01411764705882353,
      "grad_norm": 2.289916515350342,
      "learning_rate": 9.009544697495374e-05,
      "loss": 3.1167,
      "step": 111
    },
    {
      "epoch": 0.01424483306836248,
      "grad_norm": 2.1832778453826904,
      "learning_rate": 8.845153630304139e-05,
      "loss": 2.8849,
      "step": 112
    },
    {
      "epoch": 0.014372019077901432,
      "grad_norm": 2.0638606548309326,
      "learning_rate": 8.681078286579311e-05,
      "loss": 2.8642,
      "step": 113
    },
    {
      "epoch": 0.01449920508744038,
      "grad_norm": 2.2622199058532715,
      "learning_rate": 8.517363522881579e-05,
      "loss": 3.1066,
      "step": 114
    },
    {
      "epoch": 0.014626391096979332,
      "grad_norm": 2.0616939067840576,
      "learning_rate": 8.35405409719266e-05,
      "loss": 2.9251,
      "step": 115
    },
    {
      "epoch": 0.014753577106518282,
      "grad_norm": 2.2342519760131836,
      "learning_rate": 8.191194656678904e-05,
      "loss": 3.1882,
      "step": 116
    },
    {
      "epoch": 0.014880763116057233,
      "grad_norm": 2.0429413318634033,
      "learning_rate": 8.028829725485199e-05,
      "loss": 3.0048,
      "step": 117
    },
    {
      "epoch": 0.015007949125596184,
      "grad_norm": 2.2607035636901855,
      "learning_rate": 7.867003692562534e-05,
      "loss": 3.0522,
      "step": 118
    },
    {
      "epoch": 0.015135135135135135,
      "grad_norm": 2.1233274936676025,
      "learning_rate": 7.705760799532485e-05,
      "loss": 2.952,
      "step": 119
    },
    {
      "epoch": 0.015262321144674086,
      "grad_norm": 2.23429274559021,
      "learning_rate": 7.54514512859201e-05,
      "loss": 2.9693,
      "step": 120
    },
    {
      "epoch": 0.015389507154213037,
      "grad_norm": 2.315385103225708,
      "learning_rate": 7.385200590461803e-05,
      "loss": 3.2038,
      "step": 121
    },
    {
      "epoch": 0.015516693163751987,
      "grad_norm": 2.2843518257141113,
      "learning_rate": 7.225970912381556e-05,
      "loss": 2.7576,
      "step": 122
    },
    {
      "epoch": 0.015643879173290937,
      "grad_norm": 2.316584825515747,
      "learning_rate": 7.067499626155354e-05,
      "loss": 3.1409,
      "step": 123
    },
    {
      "epoch": 0.015771065182829887,
      "grad_norm": 2.1097593307495117,
      "learning_rate": 6.909830056250527e-05,
      "loss": 3.0405,
      "step": 124
    },
    {
      "epoch": 0.01589825119236884,
      "grad_norm": 2.2882628440856934,
      "learning_rate": 6.753005307953167e-05,
      "loss": 2.9586,
      "step": 125
    },
    {
      "epoch": 0.01602543720190779,
      "grad_norm": 2.2434895038604736,
      "learning_rate": 6.59706825558357e-05,
      "loss": 2.8796,
      "step": 126
    },
    {
      "epoch": 0.01615262321144674,
      "grad_norm": 2.2158470153808594,
      "learning_rate": 6.442061530774834e-05,
      "loss": 3.1726,
      "step": 127
    },
    {
      "epoch": 0.01627980922098569,
      "grad_norm": 2.311504364013672,
      "learning_rate": 6.28802751081779e-05,
      "loss": 3.2291,
      "step": 128
    },
    {
      "epoch": 0.01640699523052464,
      "grad_norm": 2.22208833694458,
      "learning_rate": 6.135008307075481e-05,
      "loss": 3.2121,
      "step": 129
    },
    {
      "epoch": 0.016534181240063592,
      "grad_norm": 2.165191650390625,
      "learning_rate": 5.983045753470308e-05,
      "loss": 3.103,
      "step": 130
    },
    {
      "epoch": 0.016661367249602543,
      "grad_norm": 2.0541014671325684,
      "learning_rate": 5.832181395047098e-05,
      "loss": 2.9611,
      "step": 131
    },
    {
      "epoch": 0.016788553259141494,
      "grad_norm": 2.2373898029327393,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 2.7329,
      "step": 132
    },
    {
      "epoch": 0.016915739268680445,
      "grad_norm": 2.2604360580444336,
      "learning_rate": 5.533911931471936e-05,
      "loss": 2.983,
      "step": 133
    },
    {
      "epoch": 0.017042925278219396,
      "grad_norm": 2.3402767181396484,
      "learning_rate": 5.386588370213124e-05,
      "loss": 2.6614,
      "step": 134
    },
    {
      "epoch": 0.017170111287758347,
      "grad_norm": 2.1931848526000977,
      "learning_rate": 5.240526069629265e-05,
      "loss": 3.2408,
      "step": 135
    },
    {
      "epoch": 0.017297297297297298,
      "grad_norm": 2.2224552631378174,
      "learning_rate": 5.095764961694922e-05,
      "loss": 2.8428,
      "step": 136
    },
    {
      "epoch": 0.01742448330683625,
      "grad_norm": 2.2872660160064697,
      "learning_rate": 4.952344622651566e-05,
      "loss": 2.928,
      "step": 137
    },
    {
      "epoch": 0.0175516693163752,
      "grad_norm": 2.107144832611084,
      "learning_rate": 4.810304262187852e-05,
      "loss": 3.1571,
      "step": 138
    },
    {
      "epoch": 0.01767885532591415,
      "grad_norm": 2.1836090087890625,
      "learning_rate": 4.669682712720065e-05,
      "loss": 2.9863,
      "step": 139
    },
    {
      "epoch": 0.0178060413354531,
      "grad_norm": 2.202346086502075,
      "learning_rate": 4.530518418775733e-05,
      "loss": 3.0278,
      "step": 140
    },
    {
      "epoch": 0.017933227344992052,
      "grad_norm": 2.1937851905822754,
      "learning_rate": 4.392849426483274e-05,
      "loss": 2.8878,
      "step": 141
    },
    {
      "epoch": 0.018060413354531003,
      "grad_norm": 2.231384038925171,
      "learning_rate": 4.256713373170564e-05,
      "loss": 3.1869,
      "step": 142
    },
    {
      "epoch": 0.018187599364069953,
      "grad_norm": 2.143895387649536,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.7143,
      "step": 143
    },
    {
      "epoch": 0.018314785373608904,
      "grad_norm": 2.0842132568359375,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 3.0679,
      "step": 144
    },
    {
      "epoch": 0.018441971383147855,
      "grad_norm": 2.206463098526001,
      "learning_rate": 3.857872873103322e-05,
      "loss": 3.122,
      "step": 145
    },
    {
      "epoch": 0.018569157392686806,
      "grad_norm": 2.248577833175659,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 2.8049,
      "step": 146
    },
    {
      "epoch": 0.018696343402225757,
      "grad_norm": 2.219324827194214,
      "learning_rate": 3.600314594966834e-05,
      "loss": 3.1196,
      "step": 147
    },
    {
      "epoch": 0.018823529411764704,
      "grad_norm": 2.359001398086548,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 3.1775,
      "step": 148
    },
    {
      "epoch": 0.018950715421303655,
      "grad_norm": 2.1845834255218506,
      "learning_rate": 3.349754278861517e-05,
      "loss": 3.0865,
      "step": 149
    },
    {
      "epoch": 0.019077901430842606,
      "grad_norm": 2.240842580795288,
      "learning_rate": 3.227184283742591e-05,
      "loss": 2.7162,
      "step": 150
    },
    {
      "epoch": 0.019077901430842606,
      "eval_loss": 0.7287956476211548,
      "eval_runtime": 57.7804,
      "eval_samples_per_second": 57.303,
      "eval_steps_per_second": 28.66,
      "step": 150
    },
    {
      "epoch": 0.019205087440381557,
      "grad_norm": 2.1659834384918213,
      "learning_rate": 3.106465908814342e-05,
      "loss": 3.0083,
      "step": 151
    },
    {
      "epoch": 0.019332273449920508,
      "grad_norm": 2.5431900024414062,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 2.8827,
      "step": 152
    },
    {
      "epoch": 0.01945945945945946,
      "grad_norm": 2.1179680824279785,
      "learning_rate": 2.87071551708603e-05,
      "loss": 2.9347,
      "step": 153
    },
    {
      "epoch": 0.01958664546899841,
      "grad_norm": 2.2814908027648926,
      "learning_rate": 2.7557479520891104e-05,
      "loss": 2.939,
      "step": 154
    },
    {
      "epoch": 0.01971383147853736,
      "grad_norm": 2.2081267833709717,
      "learning_rate": 2.6427608932686843e-05,
      "loss": 3.1783,
      "step": 155
    },
    {
      "epoch": 0.01984101748807631,
      "grad_norm": 2.1636998653411865,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 2.8015,
      "step": 156
    },
    {
      "epoch": 0.019968203497615262,
      "grad_norm": 2.2725632190704346,
      "learning_rate": 2.422851302396655e-05,
      "loss": 3.0367,
      "step": 157
    },
    {
      "epoch": 0.020095389507154213,
      "grad_norm": 2.1158969402313232,
      "learning_rate": 2.315988891431412e-05,
      "loss": 2.9014,
      "step": 158
    },
    {
      "epoch": 0.020222575516693164,
      "grad_norm": 2.225064277648926,
      "learning_rate": 2.2112272123788768e-05,
      "loss": 3.0376,
      "step": 159
    },
    {
      "epoch": 0.020349761526232114,
      "grad_norm": 2.264939308166504,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 2.7356,
      "step": 160
    },
    {
      "epoch": 0.020476947535771065,
      "grad_norm": 2.242896556854248,
      "learning_rate": 2.008120031050753e-05,
      "loss": 2.7887,
      "step": 161
    },
    {
      "epoch": 0.020604133545310016,
      "grad_norm": 2.4548873901367188,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.9714,
      "step": 162
    },
    {
      "epoch": 0.020731319554848967,
      "grad_norm": 2.1999237537384033,
      "learning_rate": 1.8137518531330767e-05,
      "loss": 2.9521,
      "step": 163
    },
    {
      "epoch": 0.020858505564387918,
      "grad_norm": 2.446458101272583,
      "learning_rate": 1.7199116885197995e-05,
      "loss": 3.272,
      "step": 164
    },
    {
      "epoch": 0.02098569157392687,
      "grad_norm": 2.216688394546509,
      "learning_rate": 1.6283352173747145e-05,
      "loss": 2.9213,
      "step": 165
    },
    {
      "epoch": 0.02111287758346582,
      "grad_norm": 2.1515614986419678,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 2.9302,
      "step": 166
    },
    {
      "epoch": 0.02124006359300477,
      "grad_norm": 2.1468420028686523,
      "learning_rate": 1.4520728741446089e-05,
      "loss": 2.9918,
      "step": 167
    },
    {
      "epoch": 0.02136724960254372,
      "grad_norm": 2.5838160514831543,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 2.8896,
      "step": 168
    },
    {
      "epoch": 0.021494435612082672,
      "grad_norm": 2.196659564971924,
      "learning_rate": 1.2851575637272262e-05,
      "loss": 2.9632,
      "step": 169
    },
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 2.193552017211914,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 2.901,
      "step": 170
    },
    {
      "epoch": 0.021748807631160574,
      "grad_norm": 2.2525877952575684,
      "learning_rate": 1.1277718055638819e-05,
      "loss": 3.1768,
      "step": 171
    },
    {
      "epoch": 0.021875993640699525,
      "grad_norm": 2.2571728229522705,
      "learning_rate": 1.0527067017923654e-05,
      "loss": 3.2308,
      "step": 172
    },
    {
      "epoch": 0.022003179650238475,
      "grad_norm": 2.3145599365234375,
      "learning_rate": 9.80087698670411e-06,
      "loss": 3.1365,
      "step": 173
    },
    {
      "epoch": 0.022130365659777426,
      "grad_norm": 2.1300814151763916,
      "learning_rate": 9.09934649508375e-06,
      "loss": 2.7955,
      "step": 174
    },
    {
      "epoch": 0.022257551669316374,
      "grad_norm": 2.23616361618042,
      "learning_rate": 8.422667334494249e-06,
      "loss": 2.9142,
      "step": 175
    },
    {
      "epoch": 0.022384737678855324,
      "grad_norm": 2.1460986137390137,
      "learning_rate": 7.771024502261526e-06,
      "loss": 2.7426,
      "step": 176
    },
    {
      "epoch": 0.022511923688394275,
      "grad_norm": 2.2808210849761963,
      "learning_rate": 7.144596151029303e-06,
      "loss": 2.9775,
      "step": 177
    },
    {
      "epoch": 0.022639109697933226,
      "grad_norm": 2.477661609649658,
      "learning_rate": 6.543553540053926e-06,
      "loss": 3.4063,
      "step": 178
    },
    {
      "epoch": 0.022766295707472177,
      "grad_norm": 2.2510106563568115,
      "learning_rate": 5.968060988383883e-06,
      "loss": 3.0301,
      "step": 179
    },
    {
      "epoch": 0.022893481717011128,
      "grad_norm": 2.361362934112549,
      "learning_rate": 5.418275829936537e-06,
      "loss": 3.1077,
      "step": 180
    },
    {
      "epoch": 0.02302066772655008,
      "grad_norm": 2.293454170227051,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 3.3876,
      "step": 181
    },
    {
      "epoch": 0.02314785373608903,
      "grad_norm": 2.142216682434082,
      "learning_rate": 4.3964218465642355e-06,
      "loss": 2.8311,
      "step": 182
    },
    {
      "epoch": 0.02327503974562798,
      "grad_norm": 2.2283873558044434,
      "learning_rate": 3.924632386315186e-06,
      "loss": 3.2105,
      "step": 183
    },
    {
      "epoch": 0.02340222575516693,
      "grad_norm": 2.265622138977051,
      "learning_rate": 3.4791089722651436e-06,
      "loss": 2.9194,
      "step": 184
    },
    {
      "epoch": 0.023529411764705882,
      "grad_norm": 2.256969690322876,
      "learning_rate": 3.059973406066963e-06,
      "loss": 3.1245,
      "step": 185
    },
    {
      "epoch": 0.023656597774244833,
      "grad_norm": 2.216651439666748,
      "learning_rate": 2.667340275199426e-06,
      "loss": 3.1906,
      "step": 186
    },
    {
      "epoch": 0.023783783783783784,
      "grad_norm": 2.2530014514923096,
      "learning_rate": 2.3013169216400733e-06,
      "loss": 2.8496,
      "step": 187
    },
    {
      "epoch": 0.023910969793322735,
      "grad_norm": 2.3641066551208496,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 3.0763,
      "step": 188
    },
    {
      "epoch": 0.024038155802861685,
      "grad_norm": 2.3235628604888916,
      "learning_rate": 1.6494925127617634e-06,
      "loss": 2.8297,
      "step": 189
    },
    {
      "epoch": 0.024165341812400636,
      "grad_norm": 2.317734956741333,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 2.9774,
      "step": 190
    },
    {
      "epoch": 0.024292527821939587,
      "grad_norm": 2.316967725753784,
      "learning_rate": 1.1052129398531507e-06,
      "loss": 2.8554,
      "step": 191
    },
    {
      "epoch": 0.024419713831478538,
      "grad_norm": 2.4230763912200928,
      "learning_rate": 8.735930673024806e-07,
      "loss": 3.3244,
      "step": 192
    },
    {
      "epoch": 0.02454689984101749,
      "grad_norm": 2.1771557331085205,
      "learning_rate": 6.690733646361857e-07,
      "loss": 2.8446,
      "step": 193
    },
    {
      "epoch": 0.02467408585055644,
      "grad_norm": 2.3441531658172607,
      "learning_rate": 4.917097454988584e-07,
      "loss": 2.7098,
      "step": 194
    },
    {
      "epoch": 0.02480127186009539,
      "grad_norm": 2.175175905227661,
      "learning_rate": 3.415506993330153e-07,
      "loss": 2.7541,
      "step": 195
    },
    {
      "epoch": 0.02492845786963434,
      "grad_norm": 2.375668525695801,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 3.0021,
      "step": 196
    },
    {
      "epoch": 0.025055643879173292,
      "grad_norm": 2.134728193283081,
      "learning_rate": 1.230030851695263e-07,
      "loss": 3.1438,
      "step": 197
    },
    {
      "epoch": 0.025182829888712243,
      "grad_norm": 2.2377030849456787,
      "learning_rate": 5.467426590739511e-08,
      "loss": 2.9125,
      "step": 198
    },
    {
      "epoch": 0.025310015898251194,
      "grad_norm": 2.040388584136963,
      "learning_rate": 1.3669500753099585e-08,
      "loss": 3.0197,
      "step": 199
    },
    {
      "epoch": 0.025437201907790145,
      "grad_norm": 2.3986241817474365,
      "learning_rate": 0.0,
      "loss": 2.9025,
      "step": 200
    },
    {
      "epoch": 0.025437201907790145,
      "eval_loss": 0.7257097959518433,
      "eval_runtime": 57.7187,
      "eval_samples_per_second": 57.364,
      "eval_steps_per_second": 28.691,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1943156564099072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}