{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01687585697711212,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.437928488556059e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 8.437928488556059e-05,
      "eval_loss": NaN,
      "eval_runtime": 150.3841,
      "eval_samples_per_second": 33.182,
      "eval_steps_per_second": 16.591,
      "step": 1
    },
    {
      "epoch": 0.00016875856977112118,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0002531378546566818,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00033751713954224236,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 4.8497,
      "step": 4
    },
    {
      "epoch": 0.00042189642442780296,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0005062757093133636,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005906549941989242,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0006750342790844847,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0007594135639700454,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0008437928488556059,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 1.0189,
      "step": 10
    },
    {
      "epoch": 0.0009281721337411666,
      "grad_norm": NaN,
      "learning_rate": 0.0001999863304992469,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0010125514186267272,
      "grad_norm": NaN,
      "learning_rate": 0.00019994532573409262,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0010969307035122878,
      "grad_norm": NaN,
      "learning_rate": 0.00019987699691483048,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0011813099883978483,
      "grad_norm": NaN,
      "learning_rate": 0.00019978136272187747,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0012656892732834089,
      "grad_norm": NaN,
      "learning_rate": 0.000199658449300667,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0013500685581689694,
      "grad_norm": NaN,
      "learning_rate": 0.00019950829025450114,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0014344478430545302,
      "grad_norm": NaN,
      "learning_rate": 0.00019933092663536382,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0015188271279400908,
      "grad_norm": NaN,
      "learning_rate": 0.00019912640693269752,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0016032064128256513,
      "grad_norm": NaN,
      "learning_rate": 0.00019889478706014687,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0016875856977112118,
      "grad_norm": NaN,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0017719649825967724,
      "grad_norm": NaN,
      "learning_rate": 0.00019835050748723824,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0018563442674823332,
      "grad_norm": NaN,
      "learning_rate": 0.00019803799658748094,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0019407235523678937,
      "grad_norm": NaN,
      "learning_rate": 0.00019769868307835994,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.0020251028372534545,
      "grad_norm": NaN,
      "learning_rate": 0.0001973326597248006,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.002109482122139015,
      "grad_norm": NaN,
      "learning_rate": 0.00019694002659393305,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0021938614070245756,
      "grad_norm": NaN,
      "learning_rate": 0.00019652089102773488,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.002278240691910136,
      "grad_norm": NaN,
      "learning_rate": 0.00019607536761368484,
      "loss": 1.4068,
      "step": 27
    },
    {
      "epoch": 0.0023626199767956967,
      "grad_norm": NaN,
      "learning_rate": 0.00019560357815343577,
      "loss": 1.0135,
      "step": 28
    },
    {
      "epoch": 0.0024469992616812574,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.0025313785465668178,
      "grad_norm": NaN,
      "learning_rate": 0.00019458172417006347,
      "loss": 1.5117,
      "step": 30
    },
    {
      "epoch": 0.0026157578314523785,
      "grad_norm": NaN,
      "learning_rate": 0.00019403193901161613,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.002700137116337939,
      "grad_norm": NaN,
      "learning_rate": 0.0001934564464599461,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.0027845164012234996,
      "grad_norm": NaN,
      "learning_rate": 0.00019285540384897073,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.0028688956861090604,
      "grad_norm": NaN,
      "learning_rate": 0.00019222897549773848,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0029532749709946207,
      "grad_norm": NaN,
      "learning_rate": 0.00019157733266550575,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0030376542558801815,
      "grad_norm": NaN,
      "learning_rate": 0.00019090065350491626,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.003122033540765742,
      "grad_norm": NaN,
      "learning_rate": 0.00019019912301329592,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.0032064128256513026,
      "grad_norm": NaN,
      "learning_rate": 0.00018947293298207635,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.0032907921105368634,
      "grad_norm": NaN,
      "learning_rate": 0.0001887222819443612,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.0033751713954224237,
      "grad_norm": NaN,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0034595506803079845,
      "grad_norm": NaN,
      "learning_rate": 0.00018714842436272773,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.003543929965193545,
      "grad_norm": NaN,
      "learning_rate": 0.00018632564809575742,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.0036283092500791056,
      "grad_norm": NaN,
      "learning_rate": 0.0001854792712585539,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.0037126885349646663,
      "grad_norm": NaN,
      "learning_rate": 0.00018460952524209355,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.0037970678198502267,
      "grad_norm": NaN,
      "learning_rate": 0.00018371664782625287,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0038814471047357874,
      "grad_norm": NaN,
      "learning_rate": 0.00018280088311480201,
      "loss": 1.6448,
      "step": 46
    },
    {
      "epoch": 0.003965826389621348,
      "grad_norm": NaN,
      "learning_rate": 0.00018186248146866927,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.004050205674506909,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.004134584959392469,
      "grad_norm": NaN,
      "learning_rate": 0.0001799187996894925,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.00421896424427803,
      "grad_norm": NaN,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.00421896424427803,
      "eval_loss": NaN,
      "eval_runtime": 149.3582,
      "eval_samples_per_second": 33.41,
      "eval_steps_per_second": 16.705,
      "step": 50
    },
    {
      "epoch": 0.00430334352916359,
      "grad_norm": NaN,
      "learning_rate": 0.00017788772787621126,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.004387722814049151,
      "grad_norm": NaN,
      "learning_rate": 0.00017684011108568592,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.0044721020989347115,
      "grad_norm": NaN,
      "learning_rate": 0.0001757714869760335,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.004556481383820272,
      "grad_norm": NaN,
      "learning_rate": 0.0001746821476984154,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.004640860668705833,
      "grad_norm": NaN,
      "learning_rate": 0.00017357239106731317,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.004725239953591393,
      "grad_norm": NaN,
      "learning_rate": 0.00017244252047910892,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.004809619238476954,
      "grad_norm": NaN,
      "learning_rate": 0.00017129284482913972,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.004893998523362515,
      "grad_norm": NaN,
      "learning_rate": 0.00017012367842724887,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.004978377808248075,
      "grad_norm": NaN,
      "learning_rate": 0.0001689353409118566,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.0050627570931336355,
      "grad_norm": NaN,
      "learning_rate": 0.00016772815716257412,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.005147136378019196,
      "grad_norm": NaN,
      "learning_rate": 0.0001665024572113848,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.005231515662904757,
      "grad_norm": NaN,
      "learning_rate": 0.00016525857615241687,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.005315894947790317,
      "grad_norm": NaN,
      "learning_rate": 0.00016399685405033167,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.005400274232675878,
      "grad_norm": NaN,
      "learning_rate": 0.0001627176358473537,
      "loss": 1.2433,
      "step": 64
    },
    {
      "epoch": 0.005484653517561439,
      "grad_norm": NaN,
      "learning_rate": 0.0001614212712689668,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.005569032802446999,
      "grad_norm": NaN,
      "learning_rate": 0.00016010811472830252,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.00565341208733256,
      "grad_norm": NaN,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.005737791372218121,
      "grad_norm": NaN,
      "learning_rate": 0.00015743286626829437,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.005822170657103681,
      "grad_norm": NaN,
      "learning_rate": 0.0001560715057351673,
      "loss": 0.5183,
      "step": 69
    },
    {
      "epoch": 0.0059065499419892415,
      "grad_norm": NaN,
      "learning_rate": 0.00015469481581224272,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.005990929226874802,
      "grad_norm": NaN,
      "learning_rate": 0.0001533031728727994,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.006075308511760363,
      "grad_norm": NaN,
      "learning_rate": 0.00015189695737812152,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.006159687796645923,
      "grad_norm": NaN,
      "learning_rate": 0.0001504765537734844,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.006244067081531484,
      "grad_norm": NaN,
      "learning_rate": 0.00014904235038305083,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.006328446366417045,
      "grad_norm": NaN,
      "learning_rate": 0.00014759473930370736,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.006412825651302605,
      "grad_norm": NaN,
      "learning_rate": 0.0001461341162978688,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.0064972049361881655,
      "grad_norm": NaN,
      "learning_rate": 0.00014466088068528068,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.006581584221073727,
      "grad_norm": NaN,
      "learning_rate": 0.00014317543523384928,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.006665963505959287,
      "grad_norm": NaN,
      "learning_rate": 0.00014167818604952906,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.006750342790844847,
      "grad_norm": NaN,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.006834722075730409,
      "grad_norm": NaN,
      "learning_rate": 0.00013864991692924523,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.006919101360615969,
      "grad_norm": NaN,
      "learning_rate": 0.00013711972489182208,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.007003480645501529,
      "grad_norm": NaN,
      "learning_rate": 0.00013557938469225167,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.00708785993038709,
      "grad_norm": NaN,
      "learning_rate": 0.00013402931744416433,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.007172239215272651,
      "grad_norm": NaN,
      "learning_rate": 0.00013246994692046836,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.007256618500158211,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.0073409977850437715,
      "grad_norm": NaN,
      "learning_rate": 0.0001293250037384465,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.007425377069929333,
      "grad_norm": NaN,
      "learning_rate": 0.00012774029087618446,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.007509756354814893,
      "grad_norm": NaN,
      "learning_rate": 0.00012614799409538198,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.007594135639700453,
      "grad_norm": NaN,
      "learning_rate": 0.00012454854871407994,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.0076785149245860145,
      "grad_norm": NaN,
      "learning_rate": 0.00012294239200467516,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.007762894209471575,
      "grad_norm": NaN,
      "learning_rate": 0.0001213299630743747,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.007847273494357135,
      "grad_norm": NaN,
      "learning_rate": 0.00011971170274514802,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.007931652779242696,
      "grad_norm": NaN,
      "learning_rate": 0.000118088053433211,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.008016032064128256,
      "grad_norm": NaN,
      "learning_rate": 0.00011645945902807341,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.008100411349013818,
      "grad_norm": NaN,
      "learning_rate": 0.0001148263647711842,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.008184790633899378,
      "grad_norm": NaN,
      "learning_rate": 0.00011318921713420691,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.008269169918784939,
      "grad_norm": NaN,
      "learning_rate": 0.00011154846369695863,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.008353549203670499,
      "grad_norm": NaN,
      "learning_rate": 0.0001099045530250463,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.00843792848855606,
      "grad_norm": NaN,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.00843792848855606,
      "eval_loss": NaN,
      "eval_runtime": 149.3835,
      "eval_samples_per_second": 33.404,
      "eval_steps_per_second": 16.702,
      "step": 100
    },
    {
      "epoch": 0.00852230777344162,
      "grad_norm": NaN,
      "learning_rate": 0.00010660905843256994,
      "loss": 0.0,
      "step": 101
    },
    {
      "epoch": 0.00860668705832718,
      "grad_norm": NaN,
      "learning_rate": 0.00010495837546732224,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.008691066343212742,
      "grad_norm": NaN,
      "learning_rate": 0.00010330633693173082,
      "loss": 0.0,
      "step": 103
    },
    {
      "epoch": 0.008775445628098302,
      "grad_norm": NaN,
      "learning_rate": 0.00010165339447663587,
      "loss": 0.0,
      "step": 104
    },
    {
      "epoch": 0.008859824912983863,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.008944204197869423,
      "grad_norm": NaN,
      "learning_rate": 9.834660552336415e-05,
      "loss": 0.0,
      "step": 106
    },
    {
      "epoch": 0.009028583482754983,
      "grad_norm": NaN,
      "learning_rate": 9.669366306826919e-05,
      "loss": 2.8749,
      "step": 107
    },
    {
      "epoch": 0.009112962767640544,
      "grad_norm": NaN,
      "learning_rate": 9.504162453267777e-05,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.009197342052526106,
      "grad_norm": NaN,
      "learning_rate": 9.339094156743007e-05,
      "loss": 0.0,
      "step": 109
    },
    {
      "epoch": 0.009281721337411666,
      "grad_norm": NaN,
      "learning_rate": 9.174206545276677e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.009366100622297226,
      "grad_norm": NaN,
      "learning_rate": 9.009544697495374e-05,
      "loss": 0.0,
      "step": 111
    },
    {
      "epoch": 0.009450479907182787,
      "grad_norm": NaN,
      "learning_rate": 8.845153630304139e-05,
      "loss": 0.0,
      "step": 112
    },
    {
      "epoch": 0.009534859192068347,
      "grad_norm": NaN,
      "learning_rate": 8.681078286579311e-05,
      "loss": 3.7729,
      "step": 113
    },
    {
      "epoch": 0.009619238476953907,
      "grad_norm": NaN,
      "learning_rate": 8.517363522881579e-05,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.009703617761839468,
      "grad_norm": NaN,
      "learning_rate": 8.35405409719266e-05,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.00978799704672503,
      "grad_norm": NaN,
      "learning_rate": 8.191194656678904e-05,
      "loss": 0.0,
      "step": 116
    },
    {
      "epoch": 0.00987237633161059,
      "grad_norm": NaN,
      "learning_rate": 8.028829725485199e-05,
      "loss": 0.0,
      "step": 117
    },
    {
      "epoch": 0.00995675561649615,
      "grad_norm": NaN,
      "learning_rate": 7.867003692562534e-05,
      "loss": 0.0,
      "step": 118
    },
    {
      "epoch": 0.01004113490138171,
      "grad_norm": NaN,
      "learning_rate": 7.705760799532485e-05,
      "loss": 0.0,
      "step": 119
    },
    {
      "epoch": 0.010125514186267271,
      "grad_norm": NaN,
      "learning_rate": 7.54514512859201e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.010209893471152831,
      "grad_norm": NaN,
      "learning_rate": 7.385200590461803e-05,
      "loss": 0.0,
      "step": 121
    },
    {
      "epoch": 0.010294272756038392,
      "grad_norm": NaN,
      "learning_rate": 7.225970912381556e-05,
      "loss": 0.0,
      "step": 122
    },
    {
      "epoch": 0.010378652040923954,
      "grad_norm": NaN,
      "learning_rate": 7.067499626155354e-05,
      "loss": 0.0,
      "step": 123
    },
    {
      "epoch": 0.010463031325809514,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 124
    },
    {
      "epoch": 0.010547410610695074,
      "grad_norm": NaN,
      "learning_rate": 6.753005307953167e-05,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.010631789895580635,
      "grad_norm": NaN,
      "learning_rate": 6.59706825558357e-05,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.010716169180466195,
      "grad_norm": NaN,
      "learning_rate": 6.442061530774834e-05,
      "loss": 0.0,
      "step": 127
    },
    {
      "epoch": 0.010800548465351755,
      "grad_norm": NaN,
      "learning_rate": 6.28802751081779e-05,
      "loss": 0.7095,
      "step": 128
    },
    {
      "epoch": 0.010884927750237318,
      "grad_norm": NaN,
      "learning_rate": 6.135008307075481e-05,
      "loss": 0.0,
      "step": 129
    },
    {
      "epoch": 0.010969307035122878,
      "grad_norm": NaN,
      "learning_rate": 5.983045753470308e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.011053686320008438,
      "grad_norm": NaN,
      "learning_rate": 5.832181395047098e-05,
      "loss": 0.0,
      "step": 131
    },
    {
      "epoch": 0.011138065604893999,
      "grad_norm": NaN,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 0.0,
      "step": 132
    },
    {
      "epoch": 0.011222444889779559,
      "grad_norm": NaN,
      "learning_rate": 5.533911931471936e-05,
      "loss": 0.0,
      "step": 133
    },
    {
      "epoch": 0.01130682417466512,
      "grad_norm": NaN,
      "learning_rate": 5.386588370213124e-05,
      "loss": 0.0,
      "step": 134
    },
    {
      "epoch": 0.01139120345955068,
      "grad_norm": NaN,
      "learning_rate": 5.240526069629265e-05,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.011475582744436242,
      "grad_norm": NaN,
      "learning_rate": 5.095764961694922e-05,
      "loss": 0.0,
      "step": 136
    },
    {
      "epoch": 0.011559962029321802,
      "grad_norm": NaN,
      "learning_rate": 4.952344622651566e-05,
      "loss": 0.0,
      "step": 137
    },
    {
      "epoch": 0.011644341314207362,
      "grad_norm": NaN,
      "learning_rate": 4.810304262187852e-05,
      "loss": 0.0,
      "step": 138
    },
    {
      "epoch": 0.011728720599092923,
      "grad_norm": NaN,
      "learning_rate": 4.669682712720065e-05,
      "loss": 0.0,
      "step": 139
    },
    {
      "epoch": 0.011813099883978483,
      "grad_norm": NaN,
      "learning_rate": 4.530518418775733e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.011897479168864043,
      "grad_norm": NaN,
      "learning_rate": 4.392849426483274e-05,
      "loss": 0.0,
      "step": 141
    },
    {
      "epoch": 0.011981858453749604,
      "grad_norm": NaN,
      "learning_rate": 4.256713373170564e-05,
      "loss": 0.0,
      "step": 142
    },
    {
      "epoch": 0.012066237738635166,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 143
    },
    {
      "epoch": 0.012150617023520726,
      "grad_norm": NaN,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 0.0,
      "step": 144
    },
    {
      "epoch": 0.012234996308406286,
      "grad_norm": NaN,
      "learning_rate": 3.857872873103322e-05,
      "loss": 4.1448,
      "step": 145
    },
    {
      "epoch": 0.012319375593291847,
      "grad_norm": NaN,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 0.0,
      "step": 146
    },
    {
      "epoch": 0.012403754878177407,
      "grad_norm": NaN,
      "learning_rate": 3.600314594966834e-05,
      "loss": 0.0,
      "step": 147
    },
    {
      "epoch": 0.012488134163062967,
      "grad_norm": NaN,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 0.0,
      "step": 148
    },
    {
      "epoch": 0.01257251344794853,
      "grad_norm": NaN,
      "learning_rate": 3.349754278861517e-05,
      "loss": 0.0,
      "step": 149
    },
    {
      "epoch": 0.01265689273283409,
      "grad_norm": NaN,
      "learning_rate": 3.227184283742591e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.01265689273283409,
      "eval_loss": NaN,
      "eval_runtime": 148.9295,
      "eval_samples_per_second": 33.506,
      "eval_steps_per_second": 16.753,
      "step": 150
    },
    {
      "epoch": 0.01274127201771965,
      "grad_norm": NaN,
      "learning_rate": 3.106465908814342e-05,
      "loss": 0.826,
      "step": 151
    },
    {
      "epoch": 0.01282565130260521,
      "grad_norm": NaN,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 1.1292,
      "step": 152
    },
    {
      "epoch": 0.01291003058749077,
      "grad_norm": NaN,
      "learning_rate": 2.87071551708603e-05,
      "loss": 0.0,
      "step": 153
    },
    {
      "epoch": 0.012994409872376331,
      "grad_norm": NaN,
      "learning_rate": 2.7557479520891104e-05,
      "loss": 0.0,
      "step": 154
    },
    {
      "epoch": 0.013078789157261891,
      "grad_norm": NaN,
      "learning_rate": 2.6427608932686843e-05,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.013163168442147453,
      "grad_norm": NaN,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 0.0,
      "step": 156
    },
    {
      "epoch": 0.013247547727033014,
      "grad_norm": NaN,
      "learning_rate": 2.422851302396655e-05,
      "loss": 0.0,
      "step": 157
    },
    {
      "epoch": 0.013331927011918574,
      "grad_norm": NaN,
      "learning_rate": 2.315988891431412e-05,
      "loss": 0.0,
      "step": 158
    },
    {
      "epoch": 0.013416306296804134,
      "grad_norm": NaN,
      "learning_rate": 2.2112272123788768e-05,
      "loss": 0.0,
      "step": 159
    },
    {
      "epoch": 0.013500685581689695,
      "grad_norm": NaN,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.013585064866575255,
      "grad_norm": NaN,
      "learning_rate": 2.008120031050753e-05,
      "loss": 0.0,
      "step": 161
    },
    {
      "epoch": 0.013669444151460817,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 162
    },
    {
      "epoch": 0.013753823436346378,
      "grad_norm": NaN,
      "learning_rate": 1.8137518531330767e-05,
      "loss": 0.0,
      "step": 163
    },
    {
      "epoch": 0.013838202721231938,
      "grad_norm": NaN,
      "learning_rate": 1.7199116885197995e-05,
      "loss": 0.0,
      "step": 164
    },
    {
      "epoch": 0.013922582006117498,
      "grad_norm": NaN,
      "learning_rate": 1.6283352173747145e-05,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.014006961291003059,
      "grad_norm": NaN,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 0.0,
      "step": 166
    },
    {
      "epoch": 0.014091340575888619,
      "grad_norm": NaN,
      "learning_rate": 1.4520728741446089e-05,
      "loss": 1.0168,
      "step": 167
    },
    {
      "epoch": 0.01417571986077418,
      "grad_norm": NaN,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 0.0,
      "step": 168
    },
    {
      "epoch": 0.014260099145659741,
      "grad_norm": NaN,
      "learning_rate": 1.2851575637272262e-05,
      "loss": 0.0,
      "step": 169
    },
    {
      "epoch": 0.014344478430545302,
      "grad_norm": NaN,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.014428857715430862,
      "grad_norm": NaN,
      "learning_rate": 1.1277718055638819e-05,
      "loss": 0.0,
      "step": 171
    },
    {
      "epoch": 0.014513237000316422,
      "grad_norm": NaN,
      "learning_rate": 1.0527067017923654e-05,
      "loss": 0.0,
      "step": 172
    },
    {
      "epoch": 0.014597616285201983,
      "grad_norm": NaN,
      "learning_rate": 9.80087698670411e-06,
      "loss": 0.0,
      "step": 173
    },
    {
      "epoch": 0.014681995570087543,
      "grad_norm": NaN,
      "learning_rate": 9.09934649508375e-06,
      "loss": 0.0,
      "step": 174
    },
    {
      "epoch": 0.014766374854973103,
      "grad_norm": NaN,
      "learning_rate": 8.422667334494249e-06,
      "loss": 1.2732,
      "step": 175
    },
    {
      "epoch": 0.014850754139858665,
      "grad_norm": NaN,
      "learning_rate": 7.771024502261526e-06,
      "loss": 0.0,
      "step": 176
    },
    {
      "epoch": 0.014935133424744226,
      "grad_norm": NaN,
      "learning_rate": 7.144596151029303e-06,
      "loss": 0.8631,
      "step": 177
    },
    {
      "epoch": 0.015019512709629786,
      "grad_norm": NaN,
      "learning_rate": 6.543553540053926e-06,
      "loss": 0.0,
      "step": 178
    },
    {
      "epoch": 0.015103891994515346,
      "grad_norm": NaN,
      "learning_rate": 5.968060988383883e-06,
      "loss": 0.0,
      "step": 179
    },
    {
      "epoch": 0.015188271279400907,
      "grad_norm": NaN,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.015272650564286467,
      "grad_norm": NaN,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0,
      "step": 181
    },
    {
      "epoch": 0.015357029849172029,
      "grad_norm": NaN,
      "learning_rate": 4.3964218465642355e-06,
      "loss": 0.0,
      "step": 182
    },
    {
      "epoch": 0.01544140913405759,
      "grad_norm": NaN,
      "learning_rate": 3.924632386315186e-06,
      "loss": 0.0,
      "step": 183
    },
    {
      "epoch": 0.01552578841894315,
      "grad_norm": NaN,
      "learning_rate": 3.4791089722651436e-06,
      "loss": 0.0,
      "step": 184
    },
    {
      "epoch": 0.01561016770382871,
      "grad_norm": NaN,
      "learning_rate": 3.059973406066963e-06,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 0.01569454698871427,
      "grad_norm": NaN,
      "learning_rate": 2.667340275199426e-06,
      "loss": 0.0,
      "step": 186
    },
    {
      "epoch": 0.015778926273599832,
      "grad_norm": NaN,
      "learning_rate": 2.3013169216400733e-06,
      "loss": 0.0,
      "step": 187
    },
    {
      "epoch": 0.01586330555848539,
      "grad_norm": NaN,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 0.0,
      "step": 188
    },
    {
      "epoch": 0.015947684843370953,
      "grad_norm": NaN,
      "learning_rate": 1.6494925127617634e-06,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 0.01603206412825651,
      "grad_norm": NaN,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 2.9297,
      "step": 190
    },
    {
      "epoch": 0.016116443413142074,
      "grad_norm": NaN,
      "learning_rate": 1.1052129398531507e-06,
      "loss": 0.0,
      "step": 191
    },
    {
      "epoch": 0.016200822698027636,
      "grad_norm": NaN,
      "learning_rate": 8.735930673024806e-07,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 0.016285201982913194,
      "grad_norm": NaN,
      "learning_rate": 6.690733646361857e-07,
      "loss": 0.0,
      "step": 193
    },
    {
      "epoch": 0.016369581267798756,
      "grad_norm": NaN,
      "learning_rate": 4.917097454988584e-07,
      "loss": 0.0,
      "step": 194
    },
    {
      "epoch": 0.016453960552684315,
      "grad_norm": NaN,
      "learning_rate": 3.415506993330153e-07,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.016538339837569877,
      "grad_norm": NaN,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 0.0,
      "step": 196
    },
    {
      "epoch": 0.016622719122455436,
      "grad_norm": NaN,
      "learning_rate": 1.230030851695263e-07,
      "loss": 0.0,
      "step": 197
    },
    {
      "epoch": 0.016707098407340998,
      "grad_norm": NaN,
      "learning_rate": 5.467426590739511e-08,
      "loss": 0.0,
      "step": 198
    },
    {
      "epoch": 0.01679147769222656,
      "grad_norm": NaN,
      "learning_rate": 1.3669500753099585e-08,
      "loss": 0.0,
      "step": 199
    },
    {
      "epoch": 0.01687585697711212,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.01687585697711212,
      "eval_loss": NaN,
      "eval_runtime": 148.9584,
      "eval_samples_per_second": 33.499,
      "eval_steps_per_second": 16.75,
      "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": 3.3877984234438656e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}