{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011229567451098742,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.614783725549371e-06,
      "grad_norm": 0.6202379465103149,
      "learning_rate": 2e-05,
      "loss": 1.0531,
      "step": 1
    },
    {
      "epoch": 5.614783725549371e-06,
      "eval_loss": 1.0175226926803589,
      "eval_runtime": 21573.5423,
      "eval_samples_per_second": 1.738,
      "eval_steps_per_second": 1.738,
      "step": 1
    },
    {
      "epoch": 1.1229567451098743e-05,
      "grad_norm": 0.5498092770576477,
      "learning_rate": 4e-05,
      "loss": 1.2547,
      "step": 2
    },
    {
      "epoch": 1.6844351176648115e-05,
      "grad_norm": 0.2675076127052307,
      "learning_rate": 6e-05,
      "loss": 0.7059,
      "step": 3
    },
    {
      "epoch": 2.2459134902197485e-05,
      "grad_norm": 0.6060311198234558,
      "learning_rate": 8e-05,
      "loss": 1.031,
      "step": 4
    },
    {
      "epoch": 2.8073918627746856e-05,
      "grad_norm": 0.43954452872276306,
      "learning_rate": 0.0001,
      "loss": 0.9217,
      "step": 5
    },
    {
      "epoch": 3.368870235329623e-05,
      "grad_norm": 0.5848556160926819,
      "learning_rate": 0.00012,
      "loss": 1.3786,
      "step": 6
    },
    {
      "epoch": 3.9303486078845604e-05,
      "grad_norm": 0.6156655550003052,
      "learning_rate": 0.00014,
      "loss": 0.8794,
      "step": 7
    },
    {
      "epoch": 4.491826980439497e-05,
      "grad_norm": 0.48315155506134033,
      "learning_rate": 0.00016,
      "loss": 1.0659,
      "step": 8
    },
    {
      "epoch": 5.0533053529944345e-05,
      "grad_norm": 0.4259559214115143,
      "learning_rate": 0.00018,
      "loss": 0.702,
      "step": 9
    },
    {
      "epoch": 5.614783725549371e-05,
      "grad_norm": 0.8003010153770447,
      "learning_rate": 0.0002,
      "loss": 0.8346,
      "step": 10
    },
    {
      "epoch": 6.176262098104309e-05,
      "grad_norm": 0.4740721583366394,
      "learning_rate": 0.0001999863304992469,
      "loss": 0.7311,
      "step": 11
    },
    {
      "epoch": 6.737740470659246e-05,
      "grad_norm": 1.4049946069717407,
      "learning_rate": 0.00019994532573409262,
      "loss": 1.0161,
      "step": 12
    },
    {
      "epoch": 7.299218843214183e-05,
      "grad_norm": 1.7016016244888306,
      "learning_rate": 0.00019987699691483048,
      "loss": 0.565,
      "step": 13
    },
    {
      "epoch": 7.860697215769121e-05,
      "grad_norm": 0.5531960129737854,
      "learning_rate": 0.00019978136272187747,
      "loss": 0.5972,
      "step": 14
    },
    {
      "epoch": 8.422175588324057e-05,
      "grad_norm": 1.0788118839263916,
      "learning_rate": 0.000199658449300667,
      "loss": 1.0518,
      "step": 15
    },
    {
      "epoch": 8.983653960878994e-05,
      "grad_norm": 1.4083199501037598,
      "learning_rate": 0.00019950829025450114,
      "loss": 0.7576,
      "step": 16
    },
    {
      "epoch": 9.545132333433932e-05,
      "grad_norm": 0.8020849823951721,
      "learning_rate": 0.00019933092663536382,
      "loss": 0.7487,
      "step": 17
    },
    {
      "epoch": 0.00010106610705988869,
      "grad_norm": 0.5158109068870544,
      "learning_rate": 0.00019912640693269752,
      "loss": 0.5468,
      "step": 18
    },
    {
      "epoch": 0.00010668089078543806,
      "grad_norm": 0.7264314889907837,
      "learning_rate": 0.00019889478706014687,
      "loss": 0.679,
      "step": 19
    },
    {
      "epoch": 0.00011229567451098742,
      "grad_norm": 0.676001787185669,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.8173,
      "step": 20
    },
    {
      "epoch": 0.0001179104582365368,
      "grad_norm": 0.5240503549575806,
      "learning_rate": 0.00019835050748723824,
      "loss": 0.6014,
      "step": 21
    },
    {
      "epoch": 0.00012352524196208617,
      "grad_norm": 0.7221630811691284,
      "learning_rate": 0.00019803799658748094,
      "loss": 0.7016,
      "step": 22
    },
    {
      "epoch": 0.00012914002568763553,
      "grad_norm": 0.8355087041854858,
      "learning_rate": 0.00019769868307835994,
      "loss": 0.7144,
      "step": 23
    },
    {
      "epoch": 0.00013475480941318492,
      "grad_norm": 0.9996209144592285,
      "learning_rate": 0.0001973326597248006,
      "loss": 0.8338,
      "step": 24
    },
    {
      "epoch": 0.00014036959313873428,
      "grad_norm": 0.6815698742866516,
      "learning_rate": 0.00019694002659393305,
      "loss": 0.8459,
      "step": 25
    },
    {
      "epoch": 0.00014598437686428367,
      "grad_norm": 0.9234247207641602,
      "learning_rate": 0.00019652089102773488,
      "loss": 0.6576,
      "step": 26
    },
    {
      "epoch": 0.00015159916058983303,
      "grad_norm": 1.3168270587921143,
      "learning_rate": 0.00019607536761368484,
      "loss": 0.9701,
      "step": 27
    },
    {
      "epoch": 0.00015721394431538241,
      "grad_norm": 0.7586074471473694,
      "learning_rate": 0.00019560357815343577,
      "loss": 0.6198,
      "step": 28
    },
    {
      "epoch": 0.00016282872804093177,
      "grad_norm": 0.6276509761810303,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.912,
      "step": 29
    },
    {
      "epoch": 0.00016844351176648113,
      "grad_norm": 0.9944347739219666,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.9922,
      "step": 30
    },
    {
      "epoch": 0.00017405829549203052,
      "grad_norm": 0.772435188293457,
      "learning_rate": 0.00019403193901161613,
      "loss": 0.7621,
      "step": 31
    },
    {
      "epoch": 0.00017967307921757988,
      "grad_norm": 0.5932286977767944,
      "learning_rate": 0.0001934564464599461,
      "loss": 0.6246,
      "step": 32
    },
    {
      "epoch": 0.00018528786294312927,
      "grad_norm": 0.44153475761413574,
      "learning_rate": 0.00019285540384897073,
      "loss": 0.659,
      "step": 33
    },
    {
      "epoch": 0.00019090264666867863,
      "grad_norm": 0.5189090967178345,
      "learning_rate": 0.00019222897549773848,
      "loss": 0.6122,
      "step": 34
    },
    {
      "epoch": 0.000196517430394228,
      "grad_norm": 0.6731717586517334,
      "learning_rate": 0.00019157733266550575,
      "loss": 0.6224,
      "step": 35
    },
    {
      "epoch": 0.00020213221411977738,
      "grad_norm": 0.5189567804336548,
      "learning_rate": 0.00019090065350491626,
      "loss": 0.7545,
      "step": 36
    },
    {
      "epoch": 0.00020774699784532674,
      "grad_norm": 0.8409593105316162,
      "learning_rate": 0.00019019912301329592,
      "loss": 0.7632,
      "step": 37
    },
    {
      "epoch": 0.00021336178157087613,
      "grad_norm": 0.5888797044754028,
      "learning_rate": 0.00018947293298207635,
      "loss": 0.9602,
      "step": 38
    },
    {
      "epoch": 0.00021897656529642549,
      "grad_norm": 0.4639832377433777,
      "learning_rate": 0.0001887222819443612,
      "loss": 0.5281,
      "step": 39
    },
    {
      "epoch": 0.00022459134902197485,
      "grad_norm": 0.7274787425994873,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.5447,
      "step": 40
    },
    {
      "epoch": 0.00023020613274752423,
      "grad_norm": 0.5326807498931885,
      "learning_rate": 0.00018714842436272773,
      "loss": 0.7716,
      "step": 41
    },
    {
      "epoch": 0.0002358209164730736,
      "grad_norm": 0.5459308624267578,
      "learning_rate": 0.00018632564809575742,
      "loss": 1.0218,
      "step": 42
    },
    {
      "epoch": 0.00024143570019862298,
      "grad_norm": 0.4652407467365265,
      "learning_rate": 0.0001854792712585539,
      "loss": 0.6814,
      "step": 43
    },
    {
      "epoch": 0.00024705048392417234,
      "grad_norm": 0.4710409641265869,
      "learning_rate": 0.00018460952524209355,
      "loss": 0.624,
      "step": 44
    },
    {
      "epoch": 0.00025266526764972173,
      "grad_norm": 0.5593191385269165,
      "learning_rate": 0.00018371664782625287,
      "loss": 0.6167,
      "step": 45
    },
    {
      "epoch": 0.00025828005137527106,
      "grad_norm": 0.876891553401947,
      "learning_rate": 0.00018280088311480201,
      "loss": 0.7577,
      "step": 46
    },
    {
      "epoch": 0.00026389483510082045,
      "grad_norm": 0.6078484654426575,
      "learning_rate": 0.00018186248146866927,
      "loss": 0.4229,
      "step": 47
    },
    {
      "epoch": 0.00026950961882636984,
      "grad_norm": 0.6034438014030457,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.5671,
      "step": 48
    },
    {
      "epoch": 0.0002751244025519192,
      "grad_norm": 0.48336154222488403,
      "learning_rate": 0.0001799187996894925,
      "loss": 0.8663,
      "step": 49
    },
    {
      "epoch": 0.00028073918627746856,
      "grad_norm": 0.917046844959259,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.8188,
      "step": 50
    },
    {
      "epoch": 0.00028073918627746856,
      "eval_loss": 0.7379979491233826,
      "eval_runtime": 21585.5399,
      "eval_samples_per_second": 1.737,
      "eval_steps_per_second": 1.737,
      "step": 50
    },
    {
      "epoch": 0.00028635397000301795,
      "grad_norm": 0.6631708145141602,
      "learning_rate": 0.00017788772787621126,
      "loss": 0.7043,
      "step": 51
    },
    {
      "epoch": 0.00029196875372856733,
      "grad_norm": 0.6282797455787659,
      "learning_rate": 0.00017684011108568592,
      "loss": 0.8696,
      "step": 52
    },
    {
      "epoch": 0.00029758353745411667,
      "grad_norm": 0.6374572515487671,
      "learning_rate": 0.0001757714869760335,
      "loss": 0.6252,
      "step": 53
    },
    {
      "epoch": 0.00030319832117966605,
      "grad_norm": 0.6826508045196533,
      "learning_rate": 0.0001746821476984154,
      "loss": 0.7257,
      "step": 54
    },
    {
      "epoch": 0.00030881310490521544,
      "grad_norm": 0.6594266891479492,
      "learning_rate": 0.00017357239106731317,
      "loss": 0.9205,
      "step": 55
    },
    {
      "epoch": 0.00031442788863076483,
      "grad_norm": 0.6436939835548401,
      "learning_rate": 0.00017244252047910892,
      "loss": 0.6385,
      "step": 56
    },
    {
      "epoch": 0.00032004267235631416,
      "grad_norm": 0.5752350687980652,
      "learning_rate": 0.00017129284482913972,
      "loss": 0.7424,
      "step": 57
    },
    {
      "epoch": 0.00032565745608186355,
      "grad_norm": 0.7134163975715637,
      "learning_rate": 0.00017012367842724887,
      "loss": 0.7284,
      "step": 58
    },
    {
      "epoch": 0.00033127223980741294,
      "grad_norm": 2.738507032394409,
      "learning_rate": 0.0001689353409118566,
      "loss": 0.6917,
      "step": 59
    },
    {
      "epoch": 0.00033688702353296227,
      "grad_norm": 0.6593369245529175,
      "learning_rate": 0.00016772815716257412,
      "loss": 1.0237,
      "step": 60
    },
    {
      "epoch": 0.00034250180725851166,
      "grad_norm": 0.5328947305679321,
      "learning_rate": 0.0001665024572113848,
      "loss": 0.5792,
      "step": 61
    },
    {
      "epoch": 0.00034811659098406104,
      "grad_norm": 1.0252548456192017,
      "learning_rate": 0.00016525857615241687,
      "loss": 0.7674,
      "step": 62
    },
    {
      "epoch": 0.0003537313747096104,
      "grad_norm": 0.7161698937416077,
      "learning_rate": 0.00016399685405033167,
      "loss": 0.6849,
      "step": 63
    },
    {
      "epoch": 0.00035934615843515977,
      "grad_norm": 0.4108976721763611,
      "learning_rate": 0.0001627176358473537,
      "loss": 0.3426,
      "step": 64
    },
    {
      "epoch": 0.00036496094216070915,
      "grad_norm": 0.8395034670829773,
      "learning_rate": 0.0001614212712689668,
      "loss": 0.7893,
      "step": 65
    },
    {
      "epoch": 0.00037057572588625854,
      "grad_norm": 1.7357856035232544,
      "learning_rate": 0.00016010811472830252,
      "loss": 0.6872,
      "step": 66
    },
    {
      "epoch": 0.0003761905096118079,
      "grad_norm": 0.6169449687004089,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.7493,
      "step": 67
    },
    {
      "epoch": 0.00038180529333735726,
      "grad_norm": 0.40986934304237366,
      "learning_rate": 0.00015743286626829437,
      "loss": 0.4622,
      "step": 68
    },
    {
      "epoch": 0.00038742007706290665,
      "grad_norm": 0.9793535470962524,
      "learning_rate": 0.0001560715057351673,
      "loss": 0.6613,
      "step": 69
    },
    {
      "epoch": 0.000393034860788456,
      "grad_norm": 0.8405007123947144,
      "learning_rate": 0.00015469481581224272,
      "loss": 0.7482,
      "step": 70
    },
    {
      "epoch": 0.00039864964451400537,
      "grad_norm": 0.9131999611854553,
      "learning_rate": 0.0001533031728727994,
      "loss": 1.1605,
      "step": 71
    },
    {
      "epoch": 0.00040426442823955476,
      "grad_norm": 0.47172001004219055,
      "learning_rate": 0.00015189695737812152,
      "loss": 0.659,
      "step": 72
    },
    {
      "epoch": 0.00040987921196510414,
      "grad_norm": 0.5213868021965027,
      "learning_rate": 0.0001504765537734844,
      "loss": 0.6634,
      "step": 73
    },
    {
      "epoch": 0.0004154939956906535,
      "grad_norm": 0.8890513181686401,
      "learning_rate": 0.00014904235038305083,
      "loss": 1.0718,
      "step": 74
    },
    {
      "epoch": 0.00042110877941620286,
      "grad_norm": 0.9680766463279724,
      "learning_rate": 0.00014759473930370736,
      "loss": 0.7103,
      "step": 75
    },
    {
      "epoch": 0.00042672356314175225,
      "grad_norm": 0.4047940969467163,
      "learning_rate": 0.0001461341162978688,
      "loss": 0.71,
      "step": 76
    },
    {
      "epoch": 0.0004323383468673016,
      "grad_norm": 0.5290956497192383,
      "learning_rate": 0.00014466088068528068,
      "loss": 0.6457,
      "step": 77
    },
    {
      "epoch": 0.00043795313059285097,
      "grad_norm": 0.6832664012908936,
      "learning_rate": 0.00014317543523384928,
      "loss": 0.6552,
      "step": 78
    },
    {
      "epoch": 0.00044356791431840036,
      "grad_norm": 0.4100581407546997,
      "learning_rate": 0.00014167818604952906,
      "loss": 0.5278,
      "step": 79
    },
    {
      "epoch": 0.0004491826980439497,
      "grad_norm": 0.7382338643074036,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.8645,
      "step": 80
    },
    {
      "epoch": 0.0004547974817694991,
      "grad_norm": 0.2650225758552551,
      "learning_rate": 0.00013864991692924523,
      "loss": 0.4649,
      "step": 81
    },
    {
      "epoch": 0.00046041226549504847,
      "grad_norm": 0.367811918258667,
      "learning_rate": 0.00013711972489182208,
      "loss": 0.7294,
      "step": 82
    },
    {
      "epoch": 0.00046602704922059786,
      "grad_norm": 0.4647292494773865,
      "learning_rate": 0.00013557938469225167,
      "loss": 0.5452,
      "step": 83
    },
    {
      "epoch": 0.0004716418329461472,
      "grad_norm": 0.6576372385025024,
      "learning_rate": 0.00013402931744416433,
      "loss": 0.9787,
      "step": 84
    },
    {
      "epoch": 0.0004772566166716966,
      "grad_norm": 0.5366365313529968,
      "learning_rate": 0.00013246994692046836,
      "loss": 0.7488,
      "step": 85
    },
    {
      "epoch": 0.00048287140039724596,
      "grad_norm": 0.5728768706321716,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6648,
      "step": 86
    },
    {
      "epoch": 0.0004884861841227954,
      "grad_norm": 0.6398264169692993,
      "learning_rate": 0.0001293250037384465,
      "loss": 0.8214,
      "step": 87
    },
    {
      "epoch": 0.0004941009678483447,
      "grad_norm": 1.2357827425003052,
      "learning_rate": 0.00012774029087618446,
      "loss": 0.8501,
      "step": 88
    },
    {
      "epoch": 0.000499715751573894,
      "grad_norm": 0.394092321395874,
      "learning_rate": 0.00012614799409538198,
      "loss": 0.3837,
      "step": 89
    },
    {
      "epoch": 0.0005053305352994435,
      "grad_norm": 0.6195949912071228,
      "learning_rate": 0.00012454854871407994,
      "loss": 0.8326,
      "step": 90
    },
    {
      "epoch": 0.0005109453190249928,
      "grad_norm": 0.435367226600647,
      "learning_rate": 0.00012294239200467516,
      "loss": 0.7117,
      "step": 91
    },
    {
      "epoch": 0.0005165601027505421,
      "grad_norm": 1.041673183441162,
      "learning_rate": 0.0001213299630743747,
      "loss": 1.0454,
      "step": 92
    },
    {
      "epoch": 0.0005221748864760916,
      "grad_norm": 0.5448310375213623,
      "learning_rate": 0.00011971170274514802,
      "loss": 0.6795,
      "step": 93
    },
    {
      "epoch": 0.0005277896702016409,
      "grad_norm": 0.5703837275505066,
      "learning_rate": 0.000118088053433211,
      "loss": 0.6598,
      "step": 94
    },
    {
      "epoch": 0.0005334044539271903,
      "grad_norm": 0.4229240417480469,
      "learning_rate": 0.00011645945902807341,
      "loss": 0.4612,
      "step": 95
    },
    {
      "epoch": 0.0005390192376527397,
      "grad_norm": 0.6660332679748535,
      "learning_rate": 0.0001148263647711842,
      "loss": 0.8873,
      "step": 96
    },
    {
      "epoch": 0.000544634021378289,
      "grad_norm": 0.6834558248519897,
      "learning_rate": 0.00011318921713420691,
      "loss": 0.7653,
      "step": 97
    },
    {
      "epoch": 0.0005502488051038384,
      "grad_norm": 0.4525357186794281,
      "learning_rate": 0.00011154846369695863,
      "loss": 0.4677,
      "step": 98
    },
    {
      "epoch": 0.0005558635888293878,
      "grad_norm": 0.34924590587615967,
      "learning_rate": 0.0001099045530250463,
      "loss": 0.4567,
      "step": 99
    },
    {
      "epoch": 0.0005614783725549371,
      "grad_norm": 0.7102425694465637,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.4776,
      "step": 100
    },
    {
      "epoch": 0.0005614783725549371,
      "eval_loss": 0.7291257977485657,
      "eval_runtime": 21564.2046,
      "eval_samples_per_second": 1.739,
      "eval_steps_per_second": 1.739,
      "step": 100
    },
    {
      "epoch": 0.0005670931562804866,
      "grad_norm": 0.8440341949462891,
      "learning_rate": 0.00010660905843256994,
      "loss": 0.5559,
      "step": 101
    },
    {
      "epoch": 0.0005727079400060359,
      "grad_norm": 0.8778635859489441,
      "learning_rate": 0.00010495837546732224,
      "loss": 0.8599,
      "step": 102
    },
    {
      "epoch": 0.0005783227237315852,
      "grad_norm": 0.5961638689041138,
      "learning_rate": 0.00010330633693173082,
      "loss": 0.6385,
      "step": 103
    },
    {
      "epoch": 0.0005839375074571347,
      "grad_norm": 0.460720956325531,
      "learning_rate": 0.00010165339447663587,
      "loss": 0.4011,
      "step": 104
    },
    {
      "epoch": 0.000589552291182684,
      "grad_norm": 0.8094878196716309,
      "learning_rate": 0.0001,
      "loss": 0.7205,
      "step": 105
    },
    {
      "epoch": 0.0005951670749082333,
      "grad_norm": 0.5714880228042603,
      "learning_rate": 9.834660552336415e-05,
      "loss": 0.7492,
      "step": 106
    },
    {
      "epoch": 0.0006007818586337828,
      "grad_norm": 0.8501264452934265,
      "learning_rate": 9.669366306826919e-05,
      "loss": 0.8841,
      "step": 107
    },
    {
      "epoch": 0.0006063966423593321,
      "grad_norm": 0.6514793634414673,
      "learning_rate": 9.504162453267777e-05,
      "loss": 0.6724,
      "step": 108
    },
    {
      "epoch": 0.0006120114260848814,
      "grad_norm": 0.7907955050468445,
      "learning_rate": 9.339094156743007e-05,
      "loss": 0.454,
      "step": 109
    },
    {
      "epoch": 0.0006176262098104309,
      "grad_norm": 0.6769828200340271,
      "learning_rate": 9.174206545276677e-05,
      "loss": 0.7664,
      "step": 110
    },
    {
      "epoch": 0.0006232409935359802,
      "grad_norm": 0.6691708564758301,
      "learning_rate": 9.009544697495374e-05,
      "loss": 1.1113,
      "step": 111
    },
    {
      "epoch": 0.0006288557772615297,
      "grad_norm": 0.603244960308075,
      "learning_rate": 8.845153630304139e-05,
      "loss": 0.7398,
      "step": 112
    },
    {
      "epoch": 0.000634470560987079,
      "grad_norm": 0.5727530121803284,
      "learning_rate": 8.681078286579311e-05,
      "loss": 0.5164,
      "step": 113
    },
    {
      "epoch": 0.0006400853447126283,
      "grad_norm": 0.45102572441101074,
      "learning_rate": 8.517363522881579e-05,
      "loss": 0.4242,
      "step": 114
    },
    {
      "epoch": 0.0006457001284381778,
      "grad_norm": 0.5324817895889282,
      "learning_rate": 8.35405409719266e-05,
      "loss": 0.7243,
      "step": 115
    },
    {
      "epoch": 0.0006513149121637271,
      "grad_norm": 0.6306778788566589,
      "learning_rate": 8.191194656678904e-05,
      "loss": 0.8012,
      "step": 116
    },
    {
      "epoch": 0.0006569296958892764,
      "grad_norm": 0.6321919560432434,
      "learning_rate": 8.028829725485199e-05,
      "loss": 0.7433,
      "step": 117
    },
    {
      "epoch": 0.0006625444796148259,
      "grad_norm": 0.7640076279640198,
      "learning_rate": 7.867003692562534e-05,
      "loss": 0.6027,
      "step": 118
    },
    {
      "epoch": 0.0006681592633403752,
      "grad_norm": 0.4536445438861847,
      "learning_rate": 7.705760799532485e-05,
      "loss": 0.3564,
      "step": 119
    },
    {
      "epoch": 0.0006737740470659245,
      "grad_norm": 0.7957231998443604,
      "learning_rate": 7.54514512859201e-05,
      "loss": 0.7709,
      "step": 120
    },
    {
      "epoch": 0.000679388830791474,
      "grad_norm": 0.354618102312088,
      "learning_rate": 7.385200590461803e-05,
      "loss": 0.458,
      "step": 121
    },
    {
      "epoch": 0.0006850036145170233,
      "grad_norm": 0.6814515590667725,
      "learning_rate": 7.225970912381556e-05,
      "loss": 0.5223,
      "step": 122
    },
    {
      "epoch": 0.0006906183982425726,
      "grad_norm": 0.695183515548706,
      "learning_rate": 7.067499626155354e-05,
      "loss": 0.5944,
      "step": 123
    },
    {
      "epoch": 0.0006962331819681221,
      "grad_norm": 0.5911761522293091,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.57,
      "step": 124
    },
    {
      "epoch": 0.0007018479656936714,
      "grad_norm": 0.8290671110153198,
      "learning_rate": 6.753005307953167e-05,
      "loss": 0.7753,
      "step": 125
    },
    {
      "epoch": 0.0007074627494192208,
      "grad_norm": 0.5861778259277344,
      "learning_rate": 6.59706825558357e-05,
      "loss": 0.7765,
      "step": 126
    },
    {
      "epoch": 0.0007130775331447702,
      "grad_norm": 0.4672585725784302,
      "learning_rate": 6.442061530774834e-05,
      "loss": 0.4829,
      "step": 127
    },
    {
      "epoch": 0.0007186923168703195,
      "grad_norm": 0.47954103350639343,
      "learning_rate": 6.28802751081779e-05,
      "loss": 0.7241,
      "step": 128
    },
    {
      "epoch": 0.000724307100595869,
      "grad_norm": 0.45866596698760986,
      "learning_rate": 6.135008307075481e-05,
      "loss": 0.4806,
      "step": 129
    },
    {
      "epoch": 0.0007299218843214183,
      "grad_norm": 0.8541582226753235,
      "learning_rate": 5.983045753470308e-05,
      "loss": 0.6784,
      "step": 130
    },
    {
      "epoch": 0.0007355366680469676,
      "grad_norm": 0.6664092540740967,
      "learning_rate": 5.832181395047098e-05,
      "loss": 0.8403,
      "step": 131
    },
    {
      "epoch": 0.0007411514517725171,
      "grad_norm": 1.3184312582015991,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 0.6905,
      "step": 132
    },
    {
      "epoch": 0.0007467662354980664,
      "grad_norm": 0.5796993374824524,
      "learning_rate": 5.533911931471936e-05,
      "loss": 0.61,
      "step": 133
    },
    {
      "epoch": 0.0007523810192236157,
      "grad_norm": 0.3954677879810333,
      "learning_rate": 5.386588370213124e-05,
      "loss": 0.4762,
      "step": 134
    },
    {
      "epoch": 0.0007579958029491652,
      "grad_norm": 0.2643950581550598,
      "learning_rate": 5.240526069629265e-05,
      "loss": 0.3033,
      "step": 135
    },
    {
      "epoch": 0.0007636105866747145,
      "grad_norm": 0.749079167842865,
      "learning_rate": 5.095764961694922e-05,
      "loss": 0.8238,
      "step": 136
    },
    {
      "epoch": 0.0007692253704002639,
      "grad_norm": 0.5847424268722534,
      "learning_rate": 4.952344622651566e-05,
      "loss": 0.5255,
      "step": 137
    },
    {
      "epoch": 0.0007748401541258133,
      "grad_norm": 0.46530458331108093,
      "learning_rate": 4.810304262187852e-05,
      "loss": 0.5624,
      "step": 138
    },
    {
      "epoch": 0.0007804549378513626,
      "grad_norm": 0.49851590394973755,
      "learning_rate": 4.669682712720065e-05,
      "loss": 0.7465,
      "step": 139
    },
    {
      "epoch": 0.000786069721576912,
      "grad_norm": 0.7142413258552551,
      "learning_rate": 4.530518418775733e-05,
      "loss": 0.7593,
      "step": 140
    },
    {
      "epoch": 0.0007916845053024614,
      "grad_norm": 0.6527928113937378,
      "learning_rate": 4.392849426483274e-05,
      "loss": 0.7741,
      "step": 141
    },
    {
      "epoch": 0.0007972992890280107,
      "grad_norm": 0.377798855304718,
      "learning_rate": 4.256713373170564e-05,
      "loss": 0.3863,
      "step": 142
    },
    {
      "epoch": 0.0008029140727535601,
      "grad_norm": 0.6521917581558228,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.6036,
      "step": 143
    },
    {
      "epoch": 0.0008085288564791095,
      "grad_norm": 0.6146506071090698,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 0.6178,
      "step": 144
    },
    {
      "epoch": 0.0008141436402046588,
      "grad_norm": 0.36121559143066406,
      "learning_rate": 3.857872873103322e-05,
      "loss": 0.4544,
      "step": 145
    },
    {
      "epoch": 0.0008197584239302083,
      "grad_norm": 0.3757206201553345,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 0.6141,
      "step": 146
    },
    {
      "epoch": 0.0008253732076557576,
      "grad_norm": 0.604722261428833,
      "learning_rate": 3.600314594966834e-05,
      "loss": 0.6223,
      "step": 147
    },
    {
      "epoch": 0.000830987991381307,
      "grad_norm": 0.761726438999176,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 0.725,
      "step": 148
    },
    {
      "epoch": 0.0008366027751068564,
      "grad_norm": 0.586891233921051,
      "learning_rate": 3.349754278861517e-05,
      "loss": 0.936,
      "step": 149
    },
    {
      "epoch": 0.0008422175588324057,
      "grad_norm": 0.6373620629310608,
      "learning_rate": 3.227184283742591e-05,
      "loss": 0.9005,
      "step": 150
    },
    {
      "epoch": 0.0008422175588324057,
      "eval_loss": 0.7196696400642395,
      "eval_runtime": 21575.1375,
      "eval_samples_per_second": 1.738,
      "eval_steps_per_second": 1.738,
      "step": 150
    },
    {
      "epoch": 0.0008478323425579551,
      "grad_norm": 0.5523321628570557,
      "learning_rate": 3.106465908814342e-05,
      "loss": 0.6273,
      "step": 151
    },
    {
      "epoch": 0.0008534471262835045,
      "grad_norm": 0.5256928205490112,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 0.6441,
      "step": 152
    },
    {
      "epoch": 0.0008590619100090538,
      "grad_norm": 0.595013439655304,
      "learning_rate": 2.87071551708603e-05,
      "loss": 0.5625,
      "step": 153
    },
    {
      "epoch": 0.0008646766937346032,
      "grad_norm": 0.38558343052864075,
      "learning_rate": 2.7557479520891104e-05,
      "loss": 0.79,
      "step": 154
    },
    {
      "epoch": 0.0008702914774601526,
      "grad_norm": 0.416737824678421,
      "learning_rate": 2.6427608932686843e-05,
      "loss": 0.6048,
      "step": 155
    },
    {
      "epoch": 0.0008759062611857019,
      "grad_norm": 0.7657343745231628,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 0.6573,
      "step": 156
    },
    {
      "epoch": 0.0008815210449112513,
      "grad_norm": 1.0111124515533447,
      "learning_rate": 2.422851302396655e-05,
      "loss": 0.8601,
      "step": 157
    },
    {
      "epoch": 0.0008871358286368007,
      "grad_norm": 0.5592943429946899,
      "learning_rate": 2.315988891431412e-05,
      "loss": 0.757,
      "step": 158
    },
    {
      "epoch": 0.00089275061236235,
      "grad_norm": 0.38879042863845825,
      "learning_rate": 2.2112272123788768e-05,
      "loss": 0.5481,
      "step": 159
    },
    {
      "epoch": 0.0008983653960878994,
      "grad_norm": 0.5495730638504028,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 1.0124,
      "step": 160
    },
    {
      "epoch": 0.0009039801798134488,
      "grad_norm": 0.4455462396144867,
      "learning_rate": 2.008120031050753e-05,
      "loss": 0.6964,
      "step": 161
    },
    {
      "epoch": 0.0009095949635389982,
      "grad_norm": 0.2935314476490021,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.4621,
      "step": 162
    },
    {
      "epoch": 0.0009152097472645476,
      "grad_norm": 0.48424121737480164,
      "learning_rate": 1.8137518531330767e-05,
      "loss": 0.6099,
      "step": 163
    },
    {
      "epoch": 0.0009208245309900969,
      "grad_norm": 0.784777820110321,
      "learning_rate": 1.7199116885197995e-05,
      "loss": 0.9775,
      "step": 164
    },
    {
      "epoch": 0.0009264393147156463,
      "grad_norm": 0.37943509221076965,
      "learning_rate": 1.6283352173747145e-05,
      "loss": 0.6561,
      "step": 165
    },
    {
      "epoch": 0.0009320540984411957,
      "grad_norm": 0.5564980506896973,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 0.5258,
      "step": 166
    },
    {
      "epoch": 0.000937668882166745,
      "grad_norm": 0.5110490918159485,
      "learning_rate": 1.4520728741446089e-05,
      "loss": 0.7777,
      "step": 167
    },
    {
      "epoch": 0.0009432836658922944,
      "grad_norm": 0.7255272269248962,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 0.8582,
      "step": 168
    },
    {
      "epoch": 0.0009488984496178438,
      "grad_norm": 0.5513525605201721,
      "learning_rate": 1.2851575637272262e-05,
      "loss": 0.3705,
      "step": 169
    },
    {
      "epoch": 0.0009545132333433932,
      "grad_norm": 0.4703540802001953,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 0.746,
      "step": 170
    },
    {
      "epoch": 0.0009601280170689425,
      "grad_norm": 0.7460604906082153,
      "learning_rate": 1.1277718055638819e-05,
      "loss": 0.6982,
      "step": 171
    },
    {
      "epoch": 0.0009657428007944919,
      "grad_norm": 0.4515000879764557,
      "learning_rate": 1.0527067017923654e-05,
      "loss": 0.6835,
      "step": 172
    },
    {
      "epoch": 0.0009713575845200413,
      "grad_norm": 0.6428802013397217,
      "learning_rate": 9.80087698670411e-06,
      "loss": 0.8466,
      "step": 173
    },
    {
      "epoch": 0.0009769723682455907,
      "grad_norm": 0.5509766340255737,
      "learning_rate": 9.09934649508375e-06,
      "loss": 0.5473,
      "step": 174
    },
    {
      "epoch": 0.00098258715197114,
      "grad_norm": 0.5568180084228516,
      "learning_rate": 8.422667334494249e-06,
      "loss": 0.8137,
      "step": 175
    },
    {
      "epoch": 0.0009882019356966894,
      "grad_norm": 0.5117676258087158,
      "learning_rate": 7.771024502261526e-06,
      "loss": 0.7012,
      "step": 176
    },
    {
      "epoch": 0.0009938167194222388,
      "grad_norm": 0.42283153533935547,
      "learning_rate": 7.144596151029303e-06,
      "loss": 0.6836,
      "step": 177
    },
    {
      "epoch": 0.000999431503147788,
      "grad_norm": 0.8226689100265503,
      "learning_rate": 6.543553540053926e-06,
      "loss": 0.8315,
      "step": 178
    },
    {
      "epoch": 0.0010050462868733375,
      "grad_norm": 0.8063510656356812,
      "learning_rate": 5.968060988383883e-06,
      "loss": 0.7767,
      "step": 179
    },
    {
      "epoch": 0.001010661070598887,
      "grad_norm": 0.4655192494392395,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.4222,
      "step": 180
    },
    {
      "epoch": 0.0010162758543244361,
      "grad_norm": 0.8273990154266357,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.8631,
      "step": 181
    },
    {
      "epoch": 0.0010218906380499856,
      "grad_norm": 0.4272424876689911,
      "learning_rate": 4.3964218465642355e-06,
      "loss": 0.5201,
      "step": 182
    },
    {
      "epoch": 0.001027505421775535,
      "grad_norm": 0.39918985962867737,
      "learning_rate": 3.924632386315186e-06,
      "loss": 0.4394,
      "step": 183
    },
    {
      "epoch": 0.0010331202055010843,
      "grad_norm": 0.4294412136077881,
      "learning_rate": 3.4791089722651436e-06,
      "loss": 0.5491,
      "step": 184
    },
    {
      "epoch": 0.0010387349892266337,
      "grad_norm": 0.398103266954422,
      "learning_rate": 3.059973406066963e-06,
      "loss": 0.6337,
      "step": 185
    },
    {
      "epoch": 0.0010443497729521831,
      "grad_norm": 1.2630798816680908,
      "learning_rate": 2.667340275199426e-06,
      "loss": 0.8147,
      "step": 186
    },
    {
      "epoch": 0.0010499645566777326,
      "grad_norm": 0.3572145998477936,
      "learning_rate": 2.3013169216400733e-06,
      "loss": 0.453,
      "step": 187
    },
    {
      "epoch": 0.0010555793404032818,
      "grad_norm": 0.6993924975395203,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 0.8392,
      "step": 188
    },
    {
      "epoch": 0.0010611941241288312,
      "grad_norm": 0.4211289584636688,
      "learning_rate": 1.6494925127617634e-06,
      "loss": 0.637,
      "step": 189
    },
    {
      "epoch": 0.0010668089078543807,
      "grad_norm": 0.5733233690261841,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 0.778,
      "step": 190
    },
    {
      "epoch": 0.00107242369157993,
      "grad_norm": 0.4856647849082947,
      "learning_rate": 1.1052129398531507e-06,
      "loss": 0.5214,
      "step": 191
    },
    {
      "epoch": 0.0010780384753054793,
      "grad_norm": 0.5088161826133728,
      "learning_rate": 8.735930673024806e-07,
      "loss": 0.7683,
      "step": 192
    },
    {
      "epoch": 0.0010836532590310288,
      "grad_norm": 0.4626195430755615,
      "learning_rate": 6.690733646361857e-07,
      "loss": 0.5463,
      "step": 193
    },
    {
      "epoch": 0.001089268042756578,
      "grad_norm": 0.32035353779792786,
      "learning_rate": 4.917097454988584e-07,
      "loss": 0.2829,
      "step": 194
    },
    {
      "epoch": 0.0010948828264821275,
      "grad_norm": 1.2485867738723755,
      "learning_rate": 3.415506993330153e-07,
      "loss": 0.6357,
      "step": 195
    },
    {
      "epoch": 0.001100497610207677,
      "grad_norm": 0.6193792819976807,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 0.8182,
      "step": 196
    },
    {
      "epoch": 0.0011061123939332261,
      "grad_norm": 0.6518222093582153,
      "learning_rate": 1.230030851695263e-07,
      "loss": 0.7356,
      "step": 197
    },
    {
      "epoch": 0.0011117271776587756,
      "grad_norm": 0.6630931496620178,
      "learning_rate": 5.467426590739511e-08,
      "loss": 0.738,
      "step": 198
    },
    {
      "epoch": 0.001117341961384325,
      "grad_norm": 0.5655919909477234,
      "learning_rate": 1.3669500753099585e-08,
      "loss": 0.6549,
      "step": 199
    },
    {
      "epoch": 0.0011229567451098742,
      "grad_norm": 0.4997493624687195,
      "learning_rate": 0.0,
      "loss": 0.6157,
      "step": 200
    },
    {
      "epoch": 0.0011229567451098742,
      "eval_loss": 0.7180939316749573,
      "eval_runtime": 21573.751,
      "eval_samples_per_second": 1.738,
      "eval_steps_per_second": 1.738,
      "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": 1.477589814214656e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}