{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9976905311778291,
  "eval_steps": 500,
  "global_step": 162,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006158583525789068,
      "grad_norm": 1.4914512634277344,
      "learning_rate": 2e-05,
      "loss": 2.3404,
      "step": 1
    },
    {
      "epoch": 0.012317167051578136,
      "grad_norm": 1.486335039138794,
      "learning_rate": 4e-05,
      "loss": 2.3428,
      "step": 2
    },
    {
      "epoch": 0.018475750577367205,
      "grad_norm": 1.4762102365493774,
      "learning_rate": 6e-05,
      "loss": 2.3374,
      "step": 3
    },
    {
      "epoch": 0.024634334103156273,
      "grad_norm": 1.5677003860473633,
      "learning_rate": 8e-05,
      "loss": 2.3111,
      "step": 4
    },
    {
      "epoch": 0.030792917628945343,
      "grad_norm": 1.5895426273345947,
      "learning_rate": 0.0001,
      "loss": 2.2003,
      "step": 5
    },
    {
      "epoch": 0.03695150115473441,
      "grad_norm": 1.4371826648712158,
      "learning_rate": 0.00012,
      "loss": 2.0329,
      "step": 6
    },
    {
      "epoch": 0.04311008468052348,
      "grad_norm": 1.3726378679275513,
      "learning_rate": 0.00014,
      "loss": 1.8007,
      "step": 7
    },
    {
      "epoch": 0.049268668206312545,
      "grad_norm": 1.4886671304702759,
      "learning_rate": 0.00016,
      "loss": 1.5998,
      "step": 8
    },
    {
      "epoch": 0.05542725173210162,
      "grad_norm": 1.3068833351135254,
      "learning_rate": 0.00018,
      "loss": 1.3961,
      "step": 9
    },
    {
      "epoch": 0.061585835257890686,
      "grad_norm": 3.4257965087890625,
      "learning_rate": 0.0002,
      "loss": 1.3012,
      "step": 10
    },
    {
      "epoch": 0.06774441878367975,
      "grad_norm": 1.5885640382766724,
      "learning_rate": 0.00019999782201809226,
      "loss": 1.1308,
      "step": 11
    },
    {
      "epoch": 0.07390300230946882,
      "grad_norm": 0.9890074729919434,
      "learning_rate": 0.00019999128816724108,
      "loss": 1.0712,
      "step": 12
    },
    {
      "epoch": 0.0800615858352579,
      "grad_norm": 0.9384965300559998,
      "learning_rate": 0.00019998039873205868,
      "loss": 1.0627,
      "step": 13
    },
    {
      "epoch": 0.08622016936104696,
      "grad_norm": 3.847111225128174,
      "learning_rate": 0.0001999651541868849,
      "loss": 1.01,
      "step": 14
    },
    {
      "epoch": 0.09237875288683603,
      "grad_norm": 1.0700613260269165,
      "learning_rate": 0.00019994555519576662,
      "loss": 1.0198,
      "step": 15
    },
    {
      "epoch": 0.09853733641262509,
      "grad_norm": 3.9324963092803955,
      "learning_rate": 0.00019992160261242877,
      "loss": 1.0316,
      "step": 16
    },
    {
      "epoch": 0.10469591993841416,
      "grad_norm": 0.8849812150001526,
      "learning_rate": 0.00019989329748023725,
      "loss": 0.9896,
      "step": 17
    },
    {
      "epoch": 0.11085450346420324,
      "grad_norm": 0.5666069984436035,
      "learning_rate": 0.00019986064103215339,
      "loss": 0.9734,
      "step": 18
    },
    {
      "epoch": 0.1170130869899923,
      "grad_norm": 0.4113065302371979,
      "learning_rate": 0.0001998236346906802,
      "loss": 0.9253,
      "step": 19
    },
    {
      "epoch": 0.12317167051578137,
      "grad_norm": 0.3489767909049988,
      "learning_rate": 0.00019978228006780054,
      "loss": 0.9113,
      "step": 20
    },
    {
      "epoch": 0.12933025404157045,
      "grad_norm": 1.2077497243881226,
      "learning_rate": 0.00019973657896490686,
      "loss": 0.9194,
      "step": 21
    },
    {
      "epoch": 0.1354888375673595,
      "grad_norm": 0.4487021863460541,
      "learning_rate": 0.00019968653337272261,
      "loss": 0.9058,
      "step": 22
    },
    {
      "epoch": 0.14164742109314857,
      "grad_norm": 0.35114091634750366,
      "learning_rate": 0.0001996321454712157,
      "loss": 0.9066,
      "step": 23
    },
    {
      "epoch": 0.14780600461893764,
      "grad_norm": 0.3634772300720215,
      "learning_rate": 0.00019957341762950344,
      "loss": 0.913,
      "step": 24
    },
    {
      "epoch": 0.15396458814472672,
      "grad_norm": 0.4948749244213104,
      "learning_rate": 0.0001995103524057494,
      "loss": 0.8944,
      "step": 25
    },
    {
      "epoch": 0.1601231716705158,
      "grad_norm": 0.3144727051258087,
      "learning_rate": 0.00019944295254705185,
      "loss": 0.8973,
      "step": 26
    },
    {
      "epoch": 0.16628175519630484,
      "grad_norm": 0.26469510793685913,
      "learning_rate": 0.00019937122098932428,
      "loss": 0.8776,
      "step": 27
    },
    {
      "epoch": 0.1724403387220939,
      "grad_norm": 0.29824352264404297,
      "learning_rate": 0.00019929516085716734,
      "loss": 0.8521,
      "step": 28
    },
    {
      "epoch": 0.17859892224788299,
      "grad_norm": 0.2820914387702942,
      "learning_rate": 0.00019921477546373296,
      "loss": 0.862,
      "step": 29
    },
    {
      "epoch": 0.18475750577367206,
      "grad_norm": 0.3102569282054901,
      "learning_rate": 0.00019913006831057969,
      "loss": 0.8586,
      "step": 30
    },
    {
      "epoch": 0.19091608929946113,
      "grad_norm": 0.30348193645477295,
      "learning_rate": 0.0001990410430875205,
      "loss": 0.854,
      "step": 31
    },
    {
      "epoch": 0.19707467282525018,
      "grad_norm": 0.31126317381858826,
      "learning_rate": 0.00019894770367246195,
      "loss": 0.8209,
      "step": 32
    },
    {
      "epoch": 0.20323325635103925,
      "grad_norm": 0.3367297351360321,
      "learning_rate": 0.00019885005413123515,
      "loss": 0.8545,
      "step": 33
    },
    {
      "epoch": 0.20939183987682833,
      "grad_norm": 0.28940874338150024,
      "learning_rate": 0.00019874809871741876,
      "loss": 0.8561,
      "step": 34
    },
    {
      "epoch": 0.2155504234026174,
      "grad_norm": 0.3074447512626648,
      "learning_rate": 0.00019864184187215372,
      "loss": 0.8495,
      "step": 35
    },
    {
      "epoch": 0.22170900692840648,
      "grad_norm": 0.29862889647483826,
      "learning_rate": 0.00019853128822394975,
      "loss": 0.8447,
      "step": 36
    },
    {
      "epoch": 0.22786759045419552,
      "grad_norm": 0.3074705898761749,
      "learning_rate": 0.0001984164425884838,
      "loss": 0.8199,
      "step": 37
    },
    {
      "epoch": 0.2340261739799846,
      "grad_norm": 0.2626888155937195,
      "learning_rate": 0.0001982973099683902,
      "loss": 0.8289,
      "step": 38
    },
    {
      "epoch": 0.24018475750577367,
      "grad_norm": 0.26036959886550903,
      "learning_rate": 0.00019817389555304272,
      "loss": 0.8244,
      "step": 39
    },
    {
      "epoch": 0.24634334103156275,
      "grad_norm": 0.2532216012477875,
      "learning_rate": 0.0001980462047183287,
      "loss": 0.8236,
      "step": 40
    },
    {
      "epoch": 0.2525019245573518,
      "grad_norm": 0.30278533697128296,
      "learning_rate": 0.0001979142430264146,
      "loss": 0.8207,
      "step": 41
    },
    {
      "epoch": 0.2586605080831409,
      "grad_norm": 0.29070666432380676,
      "learning_rate": 0.00019777801622550408,
      "loss": 0.823,
      "step": 42
    },
    {
      "epoch": 0.26481909160892997,
      "grad_norm": 0.2718726694583893,
      "learning_rate": 0.00019763753024958723,
      "loss": 0.8054,
      "step": 43
    },
    {
      "epoch": 0.270977675134719,
      "grad_norm": 0.25870487093925476,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.8118,
      "step": 44
    },
    {
      "epoch": 0.27713625866050806,
      "grad_norm": 0.2909790873527527,
      "learning_rate": 0.0001973438054360693,
      "loss": 0.8101,
      "step": 45
    },
    {
      "epoch": 0.28329484218629714,
      "grad_norm": 0.30481499433517456,
      "learning_rate": 0.00019719057939301477,
      "loss": 0.8394,
      "step": 46
    },
    {
      "epoch": 0.2894534257120862,
      "grad_norm": 0.2736552059650421,
      "learning_rate": 0.0001970331197634898,
      "loss": 0.7932,
      "step": 47
    },
    {
      "epoch": 0.2956120092378753,
      "grad_norm": 0.250683456659317,
      "learning_rate": 0.00019687143340637887,
      "loss": 0.7907,
      "step": 48
    },
    {
      "epoch": 0.30177059276366436,
      "grad_norm": 0.32575681805610657,
      "learning_rate": 0.00019670552736468118,
      "loss": 0.8022,
      "step": 49
    },
    {
      "epoch": 0.30792917628945343,
      "grad_norm": 0.3301404118537903,
      "learning_rate": 0.00019653540886520386,
      "loss": 0.8163,
      "step": 50
    },
    {
      "epoch": 0.3140877598152425,
      "grad_norm": 0.31461504101753235,
      "learning_rate": 0.00019636108531824724,
      "loss": 0.8111,
      "step": 51
    },
    {
      "epoch": 0.3202463433410316,
      "grad_norm": 0.2696295380592346,
      "learning_rate": 0.00019618256431728194,
      "loss": 0.7953,
      "step": 52
    },
    {
      "epoch": 0.32640492686682065,
      "grad_norm": 0.29559096693992615,
      "learning_rate": 0.0001959998536386181,
      "loss": 0.7759,
      "step": 53
    },
    {
      "epoch": 0.3325635103926097,
      "grad_norm": 0.2746593654155731,
      "learning_rate": 0.0001958129612410668,
      "loss": 0.7817,
      "step": 54
    },
    {
      "epoch": 0.33872209391839875,
      "grad_norm": 0.30077093839645386,
      "learning_rate": 0.0001956218952655933,
      "loss": 0.7965,
      "step": 55
    },
    {
      "epoch": 0.3448806774441878,
      "grad_norm": 0.2864063084125519,
      "learning_rate": 0.00019542666403496233,
      "loss": 0.812,
      "step": 56
    },
    {
      "epoch": 0.3510392609699769,
      "grad_norm": 0.3612823784351349,
      "learning_rate": 0.0001952272760533756,
      "loss": 0.7652,
      "step": 57
    },
    {
      "epoch": 0.35719784449576597,
      "grad_norm": 0.28117987513542175,
      "learning_rate": 0.00019502374000610151,
      "loss": 0.7982,
      "step": 58
    },
    {
      "epoch": 0.36335642802155504,
      "grad_norm": 0.3067573010921478,
      "learning_rate": 0.0001948160647590966,
      "loss": 0.7703,
      "step": 59
    },
    {
      "epoch": 0.3695150115473441,
      "grad_norm": 0.27148452401161194,
      "learning_rate": 0.00019460425935861948,
      "loss": 0.7795,
      "step": 60
    },
    {
      "epoch": 0.3756735950731332,
      "grad_norm": 0.35128867626190186,
      "learning_rate": 0.00019438833303083678,
      "loss": 0.7637,
      "step": 61
    },
    {
      "epoch": 0.38183217859892227,
      "grad_norm": 0.3009471297264099,
      "learning_rate": 0.00019416829518142118,
      "loss": 0.7838,
      "step": 62
    },
    {
      "epoch": 0.38799076212471134,
      "grad_norm": 0.3329865038394928,
      "learning_rate": 0.00019394415539514178,
      "loss": 0.7949,
      "step": 63
    },
    {
      "epoch": 0.39414934565050036,
      "grad_norm": 0.2731780707836151,
      "learning_rate": 0.00019371592343544656,
      "loss": 0.779,
      "step": 64
    },
    {
      "epoch": 0.40030792917628943,
      "grad_norm": 0.3036772608757019,
      "learning_rate": 0.00019348360924403713,
      "loss": 0.7665,
      "step": 65
    },
    {
      "epoch": 0.4064665127020785,
      "grad_norm": 0.28768160939216614,
      "learning_rate": 0.00019324722294043558,
      "loss": 0.7916,
      "step": 66
    },
    {
      "epoch": 0.4126250962278676,
      "grad_norm": 0.30529218912124634,
      "learning_rate": 0.0001930067748215438,
      "loss": 0.7848,
      "step": 67
    },
    {
      "epoch": 0.41878367975365666,
      "grad_norm": 0.2631685733795166,
      "learning_rate": 0.0001927622753611948,
      "loss": 0.785,
      "step": 68
    },
    {
      "epoch": 0.42494226327944573,
      "grad_norm": 0.33626529574394226,
      "learning_rate": 0.0001925137352096966,
      "loss": 0.7696,
      "step": 69
    },
    {
      "epoch": 0.4311008468052348,
      "grad_norm": 0.30560940504074097,
      "learning_rate": 0.0001922611651933683,
      "loss": 0.7623,
      "step": 70
    },
    {
      "epoch": 0.4372594303310239,
      "grad_norm": 0.31474098563194275,
      "learning_rate": 0.0001920045763140684,
      "loss": 0.7909,
      "step": 71
    },
    {
      "epoch": 0.44341801385681295,
      "grad_norm": 0.2986692488193512,
      "learning_rate": 0.00019174397974871564,
      "loss": 0.7837,
      "step": 72
    },
    {
      "epoch": 0.44957659738260203,
      "grad_norm": 0.2956785261631012,
      "learning_rate": 0.0001914793868488021,
      "loss": 0.7721,
      "step": 73
    },
    {
      "epoch": 0.45573518090839105,
      "grad_norm": 0.34299513697624207,
      "learning_rate": 0.0001912108091398988,
      "loss": 0.7595,
      "step": 74
    },
    {
      "epoch": 0.4618937644341801,
      "grad_norm": 0.2858146131038666,
      "learning_rate": 0.0001909382583211535,
      "loss": 0.77,
      "step": 75
    },
    {
      "epoch": 0.4680523479599692,
      "grad_norm": 0.2714357078075409,
      "learning_rate": 0.0001906617462647813,
      "loss": 0.755,
      "step": 76
    },
    {
      "epoch": 0.47421093148575827,
      "grad_norm": 0.2805250287055969,
      "learning_rate": 0.0001903812850155472,
      "loss": 0.7572,
      "step": 77
    },
    {
      "epoch": 0.48036951501154734,
      "grad_norm": 0.321464866399765,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.7259,
      "step": 78
    },
    {
      "epoch": 0.4865280985373364,
      "grad_norm": 0.27994561195373535,
      "learning_rate": 0.00018980856397714913,
      "loss": 0.7779,
      "step": 79
    },
    {
      "epoch": 0.4926866820631255,
      "grad_norm": 0.3206578195095062,
      "learning_rate": 0.00018951632913550626,
      "loss": 0.7599,
      "step": 80
    },
    {
      "epoch": 0.49884526558891457,
      "grad_norm": 0.30579233169555664,
      "learning_rate": 0.00018922019499495725,
      "loss": 0.763,
      "step": 81
    },
    {
      "epoch": 0.5050038491147036,
      "grad_norm": 0.2705940902233124,
      "learning_rate": 0.0001889201744549981,
      "loss": 0.7436,
      "step": 82
    },
    {
      "epoch": 0.5111624326404927,
      "grad_norm": 0.36793988943099976,
      "learning_rate": 0.00018861628058441506,
      "loss": 0.7489,
      "step": 83
    },
    {
      "epoch": 0.5173210161662818,
      "grad_norm": 0.30018600821495056,
      "learning_rate": 0.00018830852662071507,
      "loss": 0.7479,
      "step": 84
    },
    {
      "epoch": 0.5234795996920708,
      "grad_norm": 0.2857201397418976,
      "learning_rate": 0.00018799692596954947,
      "loss": 0.7584,
      "step": 85
    },
    {
      "epoch": 0.5296381832178599,
      "grad_norm": 0.3345021903514862,
      "learning_rate": 0.0001876814922041299,
      "loss": 0.7589,
      "step": 86
    },
    {
      "epoch": 0.535796766743649,
      "grad_norm": 0.2717898488044739,
      "learning_rate": 0.00018736223906463696,
      "loss": 0.7658,
      "step": 87
    },
    {
      "epoch": 0.541955350269438,
      "grad_norm": 0.30215781927108765,
      "learning_rate": 0.00018703918045762197,
      "loss": 0.7836,
      "step": 88
    },
    {
      "epoch": 0.5481139337952271,
      "grad_norm": 0.2765495479106903,
      "learning_rate": 0.0001867123304554009,
      "loss": 0.7556,
      "step": 89
    },
    {
      "epoch": 0.5542725173210161,
      "grad_norm": 0.31692612171173096,
      "learning_rate": 0.00018638170329544164,
      "loss": 0.7684,
      "step": 90
    },
    {
      "epoch": 0.5604311008468053,
      "grad_norm": 0.273282915353775,
      "learning_rate": 0.00018604731337974357,
      "loss": 0.7544,
      "step": 91
    },
    {
      "epoch": 0.5665896843725943,
      "grad_norm": 0.2583194971084595,
      "learning_rate": 0.00018570917527421048,
      "loss": 0.7469,
      "step": 92
    },
    {
      "epoch": 0.5727482678983834,
      "grad_norm": 0.287936270236969,
      "learning_rate": 0.00018536730370801585,
      "loss": 0.7417,
      "step": 93
    },
    {
      "epoch": 0.5789068514241724,
      "grad_norm": 0.31012046337127686,
      "learning_rate": 0.00018502171357296144,
      "loss": 0.7405,
      "step": 94
    },
    {
      "epoch": 0.5850654349499615,
      "grad_norm": 0.30453142523765564,
      "learning_rate": 0.00018467241992282843,
      "loss": 0.7688,
      "step": 95
    },
    {
      "epoch": 0.5912240184757506,
      "grad_norm": 0.2779741585254669,
      "learning_rate": 0.00018431943797272187,
      "loss": 0.7396,
      "step": 96
    },
    {
      "epoch": 0.5973826020015397,
      "grad_norm": 0.29110845923423767,
      "learning_rate": 0.00018396278309840779,
      "loss": 0.7556,
      "step": 97
    },
    {
      "epoch": 0.6035411855273287,
      "grad_norm": 0.315677285194397,
      "learning_rate": 0.00018360247083564342,
      "loss": 0.749,
      "step": 98
    },
    {
      "epoch": 0.6096997690531177,
      "grad_norm": 0.3191000521183014,
      "learning_rate": 0.00018323851687950055,
      "loss": 0.7548,
      "step": 99
    },
    {
      "epoch": 0.6158583525789069,
      "grad_norm": 0.28777754306793213,
      "learning_rate": 0.00018287093708368188,
      "loss": 0.7625,
      "step": 100
    },
    {
      "epoch": 0.6220169361046959,
      "grad_norm": 0.30834269523620605,
      "learning_rate": 0.00018249974745983023,
      "loss": 0.7605,
      "step": 101
    },
    {
      "epoch": 0.628175519630485,
      "grad_norm": 0.31846028566360474,
      "learning_rate": 0.00018212496417683137,
      "loss": 0.7715,
      "step": 102
    },
    {
      "epoch": 0.634334103156274,
      "grad_norm": 0.3188404142856598,
      "learning_rate": 0.00018174660356010943,
      "loss": 0.7661,
      "step": 103
    },
    {
      "epoch": 0.6404926866820632,
      "grad_norm": 0.2989709973335266,
      "learning_rate": 0.00018136468209091602,
      "loss": 0.728,
      "step": 104
    },
    {
      "epoch": 0.6466512702078522,
      "grad_norm": 0.31583070755004883,
      "learning_rate": 0.0001809792164056121,
      "loss": 0.7751,
      "step": 105
    },
    {
      "epoch": 0.6528098537336413,
      "grad_norm": 0.2666497528553009,
      "learning_rate": 0.0001805902232949435,
      "loss": 0.7407,
      "step": 106
    },
    {
      "epoch": 0.6589684372594303,
      "grad_norm": 0.32868844270706177,
      "learning_rate": 0.0001801977197033093,
      "loss": 0.7429,
      "step": 107
    },
    {
      "epoch": 0.6651270207852193,
      "grad_norm": 0.3197931945323944,
      "learning_rate": 0.000179801722728024,
      "loss": 0.746,
      "step": 108
    },
    {
      "epoch": 0.6712856043110085,
      "grad_norm": 0.29100263118743896,
      "learning_rate": 0.00017940224961857242,
      "loss": 0.7483,
      "step": 109
    },
    {
      "epoch": 0.6774441878367975,
      "grad_norm": 0.3278297185897827,
      "learning_rate": 0.00017899931777585882,
      "loss": 0.7619,
      "step": 110
    },
    {
      "epoch": 0.6836027713625866,
      "grad_norm": 0.3008161783218384,
      "learning_rate": 0.00017859294475144837,
      "loss": 0.7464,
      "step": 111
    },
    {
      "epoch": 0.6897613548883756,
      "grad_norm": 0.26044347882270813,
      "learning_rate": 0.000178183148246803,
      "loss": 0.7408,
      "step": 112
    },
    {
      "epoch": 0.6959199384141648,
      "grad_norm": 0.3036176562309265,
      "learning_rate": 0.00017776994611251015,
      "loss": 0.7614,
      "step": 113
    },
    {
      "epoch": 0.7020785219399538,
      "grad_norm": 0.3001931309700012,
      "learning_rate": 0.00017735335634750532,
      "loss": 0.7308,
      "step": 114
    },
    {
      "epoch": 0.7082371054657429,
      "grad_norm": 0.27744966745376587,
      "learning_rate": 0.00017693339709828792,
      "loss": 0.7456,
      "step": 115
    },
    {
      "epoch": 0.7143956889915319,
      "grad_norm": 0.2697376012802124,
      "learning_rate": 0.00017651008665813081,
      "loss": 0.7456,
      "step": 116
    },
    {
      "epoch": 0.7205542725173211,
      "grad_norm": 0.2659561336040497,
      "learning_rate": 0.0001760834434662837,
      "loss": 0.7262,
      "step": 117
    },
    {
      "epoch": 0.7267128560431101,
      "grad_norm": 0.29246559739112854,
      "learning_rate": 0.0001756534861071696,
      "loss": 0.7433,
      "step": 118
    },
    {
      "epoch": 0.7328714395688991,
      "grad_norm": 0.2959323525428772,
      "learning_rate": 0.00017522023330957548,
      "loss": 0.7512,
      "step": 119
    },
    {
      "epoch": 0.7390300230946882,
      "grad_norm": 0.26138290762901306,
      "learning_rate": 0.00017478370394583646,
      "loss": 0.7503,
      "step": 120
    },
    {
      "epoch": 0.7451886066204773,
      "grad_norm": 0.26741594076156616,
      "learning_rate": 0.00017434391703101363,
      "loss": 0.7582,
      "step": 121
    },
    {
      "epoch": 0.7513471901462664,
      "grad_norm": 0.28922754526138306,
      "learning_rate": 0.00017390089172206592,
      "loss": 0.7405,
      "step": 122
    },
    {
      "epoch": 0.7575057736720554,
      "grad_norm": 0.2668907344341278,
      "learning_rate": 0.00017345464731701547,
      "loss": 0.7381,
      "step": 123
    },
    {
      "epoch": 0.7636643571978445,
      "grad_norm": 0.27399054169654846,
      "learning_rate": 0.00017300520325410701,
      "loss": 0.7413,
      "step": 124
    },
    {
      "epoch": 0.7698229407236336,
      "grad_norm": 0.29532185196876526,
      "learning_rate": 0.0001725525791109614,
      "loss": 0.7709,
      "step": 125
    },
    {
      "epoch": 0.7759815242494227,
      "grad_norm": 0.3103969097137451,
      "learning_rate": 0.0001720967946037225,
      "loss": 0.7406,
      "step": 126
    },
    {
      "epoch": 0.7821401077752117,
      "grad_norm": 0.309108704328537,
      "learning_rate": 0.0001716378695861985,
      "loss": 0.7698,
      "step": 127
    },
    {
      "epoch": 0.7882986913010007,
      "grad_norm": 0.2896479070186615,
      "learning_rate": 0.00017117582404899712,
      "loss": 0.7417,
      "step": 128
    },
    {
      "epoch": 0.7944572748267898,
      "grad_norm": 0.28942593932151794,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.7234,
      "step": 129
    },
    {
      "epoch": 0.8006158583525789,
      "grad_norm": 0.2783251702785492,
      "learning_rate": 0.00017024245205675986,
      "loss": 0.7441,
      "step": 130
    },
    {
      "epoch": 0.806774441878368,
      "grad_norm": 0.3195393979549408,
      "learning_rate": 0.00016977116625907024,
      "loss": 0.7407,
      "step": 131
    },
    {
      "epoch": 0.812933025404157,
      "grad_norm": 0.27995389699935913,
      "learning_rate": 0.0001692968412546247,
      "loss": 0.7616,
      "step": 132
    },
    {
      "epoch": 0.8190916089299461,
      "grad_norm": 0.26950138807296753,
      "learning_rate": 0.0001688194977048488,
      "loss": 0.7261,
      "step": 133
    },
    {
      "epoch": 0.8252501924557352,
      "grad_norm": 0.28609132766723633,
      "learning_rate": 0.00016833915640265484,
      "loss": 0.7596,
      "step": 134
    },
    {
      "epoch": 0.8314087759815243,
      "grad_norm": 0.29152774810791016,
      "learning_rate": 0.00016785583827153618,
      "loss": 0.7488,
      "step": 135
    },
    {
      "epoch": 0.8375673595073133,
      "grad_norm": 0.24516189098358154,
      "learning_rate": 0.00016736956436465573,
      "loss": 0.7213,
      "step": 136
    },
    {
      "epoch": 0.8437259430331023,
      "grad_norm": 0.2636944055557251,
      "learning_rate": 0.00016688035586392885,
      "loss": 0.7124,
      "step": 137
    },
    {
      "epoch": 0.8498845265588915,
      "grad_norm": 0.2662704288959503,
      "learning_rate": 0.00016638823407910084,
      "loss": 0.7208,
      "step": 138
    },
    {
      "epoch": 0.8560431100846805,
      "grad_norm": 0.28026285767555237,
      "learning_rate": 0.00016589322044681861,
      "loss": 0.7362,
      "step": 139
    },
    {
      "epoch": 0.8622016936104696,
      "grad_norm": 0.312272846698761,
      "learning_rate": 0.00016539533652969683,
      "loss": 0.7353,
      "step": 140
    },
    {
      "epoch": 0.8683602771362586,
      "grad_norm": 0.28158485889434814,
      "learning_rate": 0.00016489460401537874,
      "loss": 0.74,
      "step": 141
    },
    {
      "epoch": 0.8745188606620478,
      "grad_norm": 0.26379963755607605,
      "learning_rate": 0.00016439104471559156,
      "loss": 0.7342,
      "step": 142
    },
    {
      "epoch": 0.8806774441878368,
      "grad_norm": 0.3109482228755951,
      "learning_rate": 0.00016388468056519612,
      "loss": 0.7649,
      "step": 143
    },
    {
      "epoch": 0.8868360277136259,
      "grad_norm": 0.3082488477230072,
      "learning_rate": 0.00016337553362123165,
      "loss": 0.7502,
      "step": 144
    },
    {
      "epoch": 0.8929946112394149,
      "grad_norm": 0.27953189611434937,
      "learning_rate": 0.00016286362606195468,
      "loss": 0.7321,
      "step": 145
    },
    {
      "epoch": 0.8991531947652041,
      "grad_norm": 0.27005666494369507,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.7447,
      "step": 146
    },
    {
      "epoch": 0.9053117782909931,
      "grad_norm": 0.29707372188568115,
      "learning_rate": 0.0001618316184107758,
      "loss": 0.727,
      "step": 147
    },
    {
      "epoch": 0.9114703618167821,
      "grad_norm": 0.3249203860759735,
      "learning_rate": 0.00016131156327275372,
      "loss": 0.7508,
      "step": 148
    },
    {
      "epoch": 0.9176289453425712,
      "grad_norm": 0.2724114954471588,
      "learning_rate": 0.00016078883742522075,
      "loss": 0.709,
      "step": 149
    },
    {
      "epoch": 0.9237875288683602,
      "grad_norm": 0.27933382987976074,
      "learning_rate": 0.00016026346363792567,
      "loss": 0.7318,
      "step": 150
    },
    {
      "epoch": 0.9299461123941494,
      "grad_norm": 0.27181556820869446,
      "learning_rate": 0.00015973546479596052,
      "loss": 0.7686,
      "step": 151
    },
    {
      "epoch": 0.9361046959199384,
      "grad_norm": 0.27142593264579773,
      "learning_rate": 0.00015920486389876383,
      "loss": 0.7485,
      "step": 152
    },
    {
      "epoch": 0.9422632794457275,
      "grad_norm": 0.26695144176483154,
      "learning_rate": 0.0001586716840591187,
      "loss": 0.7426,
      "step": 153
    },
    {
      "epoch": 0.9484218629715165,
      "grad_norm": 0.2876656949520111,
      "learning_rate": 0.000158135948502146,
      "loss": 0.7442,
      "step": 154
    },
    {
      "epoch": 0.9545804464973057,
      "grad_norm": 0.27336934208869934,
      "learning_rate": 0.00015759768056429274,
      "loss": 0.7353,
      "step": 155
    },
    {
      "epoch": 0.9607390300230947,
      "grad_norm": 0.2817447781562805,
      "learning_rate": 0.00015705690369231551,
      "loss": 0.7552,
      "step": 156
    },
    {
      "epoch": 0.9668976135488837,
      "grad_norm": 0.284213662147522,
      "learning_rate": 0.0001565136414422592,
      "loss": 0.7398,
      "step": 157
    },
    {
      "epoch": 0.9730561970746728,
      "grad_norm": 0.2847895622253418,
      "learning_rate": 0.0001559679174784308,
      "loss": 0.7364,
      "step": 158
    },
    {
      "epoch": 0.9792147806004619,
      "grad_norm": 0.2839486598968506,
      "learning_rate": 0.00015541975557236882,
      "loss": 0.754,
      "step": 159
    },
    {
      "epoch": 0.985373364126251,
      "grad_norm": 0.2721126973628998,
      "learning_rate": 0.0001548691796018074,
      "loss": 0.7448,
      "step": 160
    },
    {
      "epoch": 0.99153194765204,
      "grad_norm": 0.2735673785209656,
      "learning_rate": 0.00015431621354963668,
      "loss": 0.7308,
      "step": 161
    },
    {
      "epoch": 0.9976905311778291,
      "grad_norm": 0.31629157066345215,
      "learning_rate": 0.00015376088150285773,
      "loss": 0.7456,
      "step": 162
    }
  ],
  "logging_steps": 1,
  "max_steps": 486,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 162,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.588141062388449e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}