{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 50,
  "global_step": 142,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014222222222222223,
      "grad_norm": 0.09173738956451416,
      "learning_rate": 0.0,
      "loss": 1.005206823348999,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 0.09365915507078171,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 1.0057916641235352,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.0689043328166008,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.9406883716583252,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 0.04593552276492119,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.8941981792449951,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.03204488381743431,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.7926980257034302,
      "step": 5
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.027753565460443497,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.8305954933166504,
      "step": 6
    },
    {
      "epoch": 0.09955555555555555,
      "grad_norm": 0.03171968460083008,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.7948952913284302,
      "step": 7
    },
    {
      "epoch": 0.11377777777777778,
      "grad_norm": 0.026748575270175934,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.7530462741851807,
      "step": 8
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.023413579910993576,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.7157606482505798,
      "step": 9
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.020688239485025406,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.7008587718009949,
      "step": 10
    },
    {
      "epoch": 0.15644444444444444,
      "grad_norm": 0.014185823500156403,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.6668463945388794,
      "step": 11
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.012938937172293663,
      "learning_rate": 5e-06,
      "loss": 0.6507903337478638,
      "step": 12
    },
    {
      "epoch": 0.18488888888888888,
      "grad_norm": 0.012045802548527718,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.6217454671859741,
      "step": 13
    },
    {
      "epoch": 0.1991111111111111,
      "grad_norm": 0.009660671465098858,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.6269917488098145,
      "step": 14
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.008694784715771675,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.5836964845657349,
      "step": 15
    },
    {
      "epoch": 0.22755555555555557,
      "grad_norm": 0.008789200335741043,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.6187424659729004,
      "step": 16
    },
    {
      "epoch": 0.24177777777777779,
      "grad_norm": 0.008197025395929813,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.5914188027381897,
      "step": 17
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.007580601144582033,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.5802223682403564,
      "step": 18
    },
    {
      "epoch": 0.2702222222222222,
      "grad_norm": 0.007013861555606127,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.5884265899658203,
      "step": 19
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.00683254050090909,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.5850374698638916,
      "step": 20
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.006111981347203255,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.5651419162750244,
      "step": 21
    },
    {
      "epoch": 0.3128888888888889,
      "grad_norm": 0.005564771592617035,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.553795576095581,
      "step": 22
    },
    {
      "epoch": 0.32711111111111113,
      "grad_norm": 0.0057683708146214485,
      "learning_rate": 1e-05,
      "loss": 0.5542658567428589,
      "step": 23
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.006690182723104954,
      "learning_rate": 9.999323662872998e-06,
      "loss": 0.5586982369422913,
      "step": 24
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.006314165890216827,
      "learning_rate": 9.99729483446475e-06,
      "loss": 0.5584714412689209,
      "step": 25
    },
    {
      "epoch": 0.36977777777777776,
      "grad_norm": 0.005813857074826956,
      "learning_rate": 9.993914063644053e-06,
      "loss": 0.5466614961624146,
      "step": 26
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.005381743889302015,
      "learning_rate": 9.989182265027232e-06,
      "loss": 0.5380265712738037,
      "step": 27
    },
    {
      "epoch": 0.3982222222222222,
      "grad_norm": 0.0049252682365477085,
      "learning_rate": 9.98310071873072e-06,
      "loss": 0.535520613193512,
      "step": 28
    },
    {
      "epoch": 0.41244444444444445,
      "grad_norm": 0.0048560877330601215,
      "learning_rate": 9.975671070024741e-06,
      "loss": 0.5377035140991211,
      "step": 29
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.004911178257316351,
      "learning_rate": 9.966895328888195e-06,
      "loss": 0.5570093989372253,
      "step": 30
    },
    {
      "epoch": 0.4408888888888889,
      "grad_norm": 0.004746970720589161,
      "learning_rate": 9.956775869464901e-06,
      "loss": 0.5285611748695374,
      "step": 31
    },
    {
      "epoch": 0.45511111111111113,
      "grad_norm": 0.0047261337749660015,
      "learning_rate": 9.945315429421307e-06,
      "loss": 0.5199858546257019,
      "step": 32
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.004447608254849911,
      "learning_rate": 9.932517109205849e-06,
      "loss": 0.5250071287155151,
      "step": 33
    },
    {
      "epoch": 0.48355555555555557,
      "grad_norm": 0.004617375787347555,
      "learning_rate": 9.918384371210178e-06,
      "loss": 0.5516105890274048,
      "step": 34
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.004378544166684151,
      "learning_rate": 9.902921038832456e-06,
      "loss": 0.5298895835876465,
      "step": 35
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.004164176061749458,
      "learning_rate": 9.886131295443003e-06,
      "loss": 0.5044555068016052,
      "step": 36
    },
    {
      "epoch": 0.5262222222222223,
      "grad_norm": 0.004092546179890633,
      "learning_rate": 9.868019683252543e-06,
      "loss": 0.5102939009666443,
      "step": 37
    },
    {
      "epoch": 0.5404444444444444,
      "grad_norm": 0.004554086830466986,
      "learning_rate": 9.848591102083375e-06,
      "loss": 0.5421494245529175,
      "step": 38
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.004217132460325956,
      "learning_rate": 9.82785080804381e-06,
      "loss": 0.5239347219467163,
      "step": 39
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.004286583047360182,
      "learning_rate": 9.805804412106197e-06,
      "loss": 0.5437066555023193,
      "step": 40
    },
    {
      "epoch": 0.5831111111111111,
      "grad_norm": 0.004261231981217861,
      "learning_rate": 9.782457878588977e-06,
      "loss": 0.5146951079368591,
      "step": 41
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.004209685139358044,
      "learning_rate": 9.75781752354311e-06,
      "loss": 0.4995099604129791,
      "step": 42
    },
    {
      "epoch": 0.6115555555555555,
      "grad_norm": 0.0039211539551615715,
      "learning_rate": 9.731890013043367e-06,
      "loss": 0.5249044299125671,
      "step": 43
    },
    {
      "epoch": 0.6257777777777778,
      "grad_norm": 0.0038641595747321844,
      "learning_rate": 9.704682361384941e-06,
      "loss": 0.4980819821357727,
      "step": 44
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.004069323651492596,
      "learning_rate": 9.676201929185809e-06,
      "loss": 0.5113821625709534,
      "step": 45
    },
    {
      "epoch": 0.6542222222222223,
      "grad_norm": 0.0038530679885298014,
      "learning_rate": 9.646456421395447e-06,
      "loss": 0.5072203278541565,
      "step": 46
    },
    {
      "epoch": 0.6684444444444444,
      "grad_norm": 0.003951605875045061,
      "learning_rate": 9.615453885210368e-06,
      "loss": 0.509921669960022,
      "step": 47
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.0038154355715960264,
      "learning_rate": 9.583202707897075e-06,
      "loss": 0.49035143852233887,
      "step": 48
    },
    {
      "epoch": 0.6968888888888889,
      "grad_norm": 0.004143900703638792,
      "learning_rate": 9.549711614523007e-06,
      "loss": 0.4858332574367523,
      "step": 49
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.0038300366140902042,
      "learning_rate": 9.514989665596114e-06,
      "loss": 0.49062296748161316,
      "step": 50
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 0.5049259662628174,
      "eval_runtime": 38.0442,
      "eval_samples_per_second": 5.257,
      "eval_steps_per_second": 2.629,
      "step": 50
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.003965203184634447,
      "learning_rate": 9.479046254613673e-06,
      "loss": 0.5013079643249512,
      "step": 51
    },
    {
      "epoch": 0.7395555555555555,
      "grad_norm": 0.003626414341852069,
      "learning_rate": 9.441891105521005e-06,
      "loss": 0.46776771545410156,
      "step": 52
    },
    {
      "epoch": 0.7537777777777778,
      "grad_norm": 0.003647371893748641,
      "learning_rate": 9.40353427008083e-06,
      "loss": 0.4870305061340332,
      "step": 53
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.0036924544256180525,
      "learning_rate": 9.3639861251539e-06,
      "loss": 0.48354169726371765,
      "step": 54
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.0037534767761826515,
      "learning_rate": 9.323257369891702e-06,
      "loss": 0.5097652673721313,
      "step": 55
    },
    {
      "epoch": 0.7964444444444444,
      "grad_norm": 0.003901001764461398,
      "learning_rate": 9.281359022841966e-06,
      "loss": 0.5023170709609985,
      "step": 56
    },
    {
      "epoch": 0.8106666666666666,
      "grad_norm": 0.0037305736914277077,
      "learning_rate": 9.238302418967757e-06,
      "loss": 0.49597933888435364,
      "step": 57
    },
    {
      "epoch": 0.8248888888888889,
      "grad_norm": 0.003764534369111061,
      "learning_rate": 9.194099206580981e-06,
      "loss": 0.504522442817688,
      "step": 58
    },
    {
      "epoch": 0.8391111111111111,
      "grad_norm": 0.004040914587676525,
      "learning_rate": 9.14876134419111e-06,
      "loss": 0.49795830249786377,
      "step": 59
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.003855582093819976,
      "learning_rate": 9.102301097269974e-06,
      "loss": 0.49624279141426086,
      "step": 60
    },
    {
      "epoch": 0.8675555555555555,
      "grad_norm": 0.003851535264402628,
      "learning_rate": 9.05473103493355e-06,
      "loss": 0.47714120149612427,
      "step": 61
    },
    {
      "epoch": 0.8817777777777778,
      "grad_norm": 0.004122862592339516,
      "learning_rate": 9.006064026541549e-06,
      "loss": 0.5046075582504272,
      "step": 62
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.0036710964050143957,
      "learning_rate": 8.956313238215824e-06,
      "loss": 0.45711296796798706,
      "step": 63
    },
    {
      "epoch": 0.9102222222222223,
      "grad_norm": 0.004037045873701572,
      "learning_rate": 8.905492129278478e-06,
      "loss": 0.4839310050010681,
      "step": 64
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.004081980790942907,
      "learning_rate": 8.85361444861063e-06,
      "loss": 0.4877704381942749,
      "step": 65
    },
    {
      "epoch": 0.9386666666666666,
      "grad_norm": 0.0037577205803245306,
      "learning_rate": 8.800694230932885e-06,
      "loss": 0.49369895458221436,
      "step": 66
    },
    {
      "epoch": 0.9528888888888889,
      "grad_norm": 0.0037781032733619213,
      "learning_rate": 8.74674579300843e-06,
      "loss": 0.4812237620353699,
      "step": 67
    },
    {
      "epoch": 0.9671111111111111,
      "grad_norm": 0.0046208929270505905,
      "learning_rate": 8.691783729769874e-06,
      "loss": 0.4722365736961365,
      "step": 68
    },
    {
      "epoch": 0.9813333333333333,
      "grad_norm": 0.004026597365736961,
      "learning_rate": 8.635822910370793e-06,
      "loss": 0.4962988495826721,
      "step": 69
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.004095569718629122,
      "learning_rate": 8.578878474163115e-06,
      "loss": 0.45991775393486023,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.006300764624029398,
      "learning_rate": 8.520965826601394e-06,
      "loss": 0.4934382140636444,
      "step": 71
    },
    {
      "epoch": 1.0142222222222221,
      "grad_norm": 0.00428728898987174,
      "learning_rate": 8.462100635075097e-06,
      "loss": 0.4847542643547058,
      "step": 72
    },
    {
      "epoch": 1.0284444444444445,
      "grad_norm": 0.004186135251075029,
      "learning_rate": 8.40229882467003e-06,
      "loss": 0.4636518955230713,
      "step": 73
    },
    {
      "epoch": 1.0426666666666666,
      "grad_norm": 0.003916833084076643,
      "learning_rate": 8.341576573860049e-06,
      "loss": 0.44187992811203003,
      "step": 74
    },
    {
      "epoch": 1.056888888888889,
      "grad_norm": 0.004144088365137577,
      "learning_rate": 8.279950310130218e-06,
      "loss": 0.467815637588501,
      "step": 75
    },
    {
      "epoch": 1.0711111111111111,
      "grad_norm": 0.004077525809407234,
      "learning_rate": 8.2174367055326e-06,
      "loss": 0.451981782913208,
      "step": 76
    },
    {
      "epoch": 1.0853333333333333,
      "grad_norm": 0.004103589337319136,
      "learning_rate": 8.154052672175888e-06,
      "loss": 0.4449639320373535,
      "step": 77
    },
    {
      "epoch": 1.0995555555555556,
      "grad_norm": 0.00439891591668129,
      "learning_rate": 8.08981535765009e-06,
      "loss": 0.47661933302879333,
      "step": 78
    },
    {
      "epoch": 1.1137777777777778,
      "grad_norm": 0.004592400509864092,
      "learning_rate": 8.024742140387506e-06,
      "loss": 0.45776277780532837,
      "step": 79
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 0.0037961499765515327,
      "learning_rate": 7.95885062496126e-06,
      "loss": 0.44757023453712463,
      "step": 80
    },
    {
      "epoch": 1.1422222222222222,
      "grad_norm": 0.003865304868668318,
      "learning_rate": 7.892158637322647e-06,
      "loss": 0.419955849647522,
      "step": 81
    },
    {
      "epoch": 1.1564444444444444,
      "grad_norm": 0.00407387875020504,
      "learning_rate": 7.824684219978591e-06,
      "loss": 0.4457795023918152,
      "step": 82
    },
    {
      "epoch": 1.1706666666666667,
      "grad_norm": 0.00370654184371233,
      "learning_rate": 7.756445627110523e-06,
      "loss": 0.45605674386024475,
      "step": 83
    },
    {
      "epoch": 1.1848888888888889,
      "grad_norm": 0.003941345028579235,
      "learning_rate": 7.68746131963598e-06,
      "loss": 0.46289366483688354,
      "step": 84
    },
    {
      "epoch": 1.199111111111111,
      "grad_norm": 0.0039403438568115234,
      "learning_rate": 7.6177499602143e-06,
      "loss": 0.45568281412124634,
      "step": 85
    },
    {
      "epoch": 1.2133333333333334,
      "grad_norm": 0.003944277763366699,
      "learning_rate": 7.547330408197695e-06,
      "loss": 0.44618040323257446,
      "step": 86
    },
    {
      "epoch": 1.2275555555555555,
      "grad_norm": 0.0040544732473790646,
      "learning_rate": 7.476221714529167e-06,
      "loss": 0.45724251866340637,
      "step": 87
    },
    {
      "epoch": 1.2417777777777779,
      "grad_norm": 0.004533152561634779,
      "learning_rate": 7.404443116588548e-06,
      "loss": 0.4806937575340271,
      "step": 88
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.004002939909696579,
      "learning_rate": 7.332014032988123e-06,
      "loss": 0.4561174213886261,
      "step": 89
    },
    {
      "epoch": 1.2702222222222221,
      "grad_norm": 0.003825302002951503,
      "learning_rate": 7.2589540583192165e-06,
      "loss": 0.4558497667312622,
      "step": 90
    },
    {
      "epoch": 1.2844444444444445,
      "grad_norm": 0.00397696765139699,
      "learning_rate": 7.185282957851175e-06,
      "loss": 0.4397018551826477,
      "step": 91
    },
    {
      "epoch": 1.2986666666666666,
      "grad_norm": 0.004289410542696714,
      "learning_rate": 7.111020662184174e-06,
      "loss": 0.45822006464004517,
      "step": 92
    },
    {
      "epoch": 1.3128888888888888,
      "grad_norm": 0.004002283327281475,
      "learning_rate": 7.036187261857289e-06,
      "loss": 0.4479483366012573,
      "step": 93
    },
    {
      "epoch": 1.3271111111111111,
      "grad_norm": 0.004231768660247326,
      "learning_rate": 6.960803001913315e-06,
      "loss": 0.4738925099372864,
      "step": 94
    },
    {
      "epoch": 1.3413333333333333,
      "grad_norm": 0.0040559363551437855,
      "learning_rate": 6.884888276421766e-06,
      "loss": 0.4614931643009186,
      "step": 95
    },
    {
      "epoch": 1.3555555555555556,
      "grad_norm": 0.003587141167372465,
      "learning_rate": 6.8084636229615786e-06,
      "loss": 0.44328922033309937,
      "step": 96
    },
    {
      "epoch": 1.3697777777777778,
      "grad_norm": 0.004009770695120096,
      "learning_rate": 6.731549717064975e-06,
      "loss": 0.44612404704093933,
      "step": 97
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.004132336005568504,
      "learning_rate": 6.654167366624009e-06,
      "loss": 0.4554000794887543,
      "step": 98
    },
    {
      "epoch": 1.3982222222222223,
      "grad_norm": 0.0041816201992332935,
      "learning_rate": 6.576337506261314e-06,
      "loss": 0.45616668462753296,
      "step": 99
    },
    {
      "epoch": 1.4124444444444444,
      "grad_norm": 0.003568898420780897,
      "learning_rate": 6.498081191666549e-06,
      "loss": 0.45816588401794434,
      "step": 100
    },
    {
      "epoch": 1.4124444444444444,
      "eval_loss": 0.4757018983364105,
      "eval_runtime": 39.6302,
      "eval_samples_per_second": 5.047,
      "eval_steps_per_second": 2.523,
      "step": 100
    },
    {
      "epoch": 1.4266666666666667,
      "grad_norm": 0.004014050588011742,
      "learning_rate": 6.419419593900109e-06,
      "loss": 0.4430053234100342,
      "step": 101
    },
    {
      "epoch": 1.4408888888888889,
      "grad_norm": 0.0039361282251775265,
      "learning_rate": 6.340373993665607e-06,
      "loss": 0.43451493978500366,
      "step": 102
    },
    {
      "epoch": 1.455111111111111,
      "grad_norm": 0.0040025534108281136,
      "learning_rate": 6.2609657755527135e-06,
      "loss": 0.4296550154685974,
      "step": 103
    },
    {
      "epoch": 1.4693333333333334,
      "grad_norm": 0.004081938415765762,
      "learning_rate": 6.1812164222518626e-06,
      "loss": 0.46728163957595825,
      "step": 104
    },
    {
      "epoch": 1.4835555555555555,
      "grad_norm": 0.0043087489902973175,
      "learning_rate": 6.101147508742456e-06,
      "loss": 0.446887731552124,
      "step": 105
    },
    {
      "epoch": 1.4977777777777779,
      "grad_norm": 0.0037424617912620306,
      "learning_rate": 6.020780696456059e-06,
      "loss": 0.43969088792800903,
      "step": 106
    },
    {
      "epoch": 1.512,
      "grad_norm": 0.003990524914115667,
      "learning_rate": 5.940137727416247e-06,
      "loss": 0.4489642381668091,
      "step": 107
    },
    {
      "epoch": 1.5262222222222221,
      "grad_norm": 0.00401579262688756,
      "learning_rate": 5.859240418356614e-06,
      "loss": 0.4380025863647461,
      "step": 108
    },
    {
      "epoch": 1.5404444444444443,
      "grad_norm": 0.0042803785763680935,
      "learning_rate": 5.778110654818602e-06,
      "loss": 0.47752195596694946,
      "step": 109
    },
    {
      "epoch": 1.5546666666666666,
      "grad_norm": 0.003838231321424246,
      "learning_rate": 5.696770385230679e-06,
      "loss": 0.4498862028121948,
      "step": 110
    },
    {
      "epoch": 1.568888888888889,
      "grad_norm": 0.0041479310020804405,
      "learning_rate": 5.615241614970546e-06,
      "loss": 0.44400298595428467,
      "step": 111
    },
    {
      "epoch": 1.5831111111111111,
      "grad_norm": 0.0038208707701414824,
      "learning_rate": 5.533546400411899e-06,
      "loss": 0.4457319378852844,
      "step": 112
    },
    {
      "epoch": 1.5973333333333333,
      "grad_norm": 0.0038792924024164677,
      "learning_rate": 5.4517068429574215e-06,
      "loss": 0.4610831141471863,
      "step": 113
    },
    {
      "epoch": 1.6115555555555554,
      "grad_norm": 0.004012539051473141,
      "learning_rate": 5.3697450830595775e-06,
      "loss": 0.4425020217895508,
      "step": 114
    },
    {
      "epoch": 1.6257777777777778,
      "grad_norm": 0.003996311221271753,
      "learning_rate": 5.287683294230855e-06,
      "loss": 0.44555309414863586,
      "step": 115
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.0037504970096051693,
      "learning_rate": 5.20554367704505e-06,
      "loss": 0.417566180229187,
      "step": 116
    },
    {
      "epoch": 1.6542222222222223,
      "grad_norm": 0.003828976536169648,
      "learning_rate": 5.123348453131242e-06,
      "loss": 0.45680171251296997,
      "step": 117
    },
    {
      "epoch": 1.6684444444444444,
      "grad_norm": 0.0040869563817977905,
      "learning_rate": 5.041119859162068e-06,
      "loss": 0.4432540535926819,
      "step": 118
    },
    {
      "epoch": 1.6826666666666665,
      "grad_norm": 0.004195951856672764,
      "learning_rate": 4.958880140837934e-06,
      "loss": 0.44924670457839966,
      "step": 119
    },
    {
      "epoch": 1.696888888888889,
      "grad_norm": 0.003907010890543461,
      "learning_rate": 4.876651546868759e-06,
      "loss": 0.43826115131378174,
      "step": 120
    },
    {
      "epoch": 1.7111111111111112,
      "grad_norm": 0.003893865505233407,
      "learning_rate": 4.794456322954953e-06,
      "loss": 0.4698702096939087,
      "step": 121
    },
    {
      "epoch": 1.7253333333333334,
      "grad_norm": 0.003987904172390699,
      "learning_rate": 4.7123167057691446e-06,
      "loss": 0.4665527045726776,
      "step": 122
    },
    {
      "epoch": 1.7395555555555555,
      "grad_norm": 0.003826166968792677,
      "learning_rate": 4.630254916940424e-06,
      "loss": 0.46612560749053955,
      "step": 123
    },
    {
      "epoch": 1.7537777777777777,
      "grad_norm": 0.0037139400374144316,
      "learning_rate": 4.548293157042581e-06,
      "loss": 0.4559047818183899,
      "step": 124
    },
    {
      "epoch": 1.768,
      "grad_norm": 0.0038443440571427345,
      "learning_rate": 4.466453599588103e-06,
      "loss": 0.4595223069190979,
      "step": 125
    },
    {
      "epoch": 1.7822222222222224,
      "grad_norm": 0.0039060397539287806,
      "learning_rate": 4.384758385029457e-06,
      "loss": 0.42560791969299316,
      "step": 126
    },
    {
      "epoch": 1.7964444444444445,
      "grad_norm": 0.0041647544130682945,
      "learning_rate": 4.3032296147693225e-06,
      "loss": 0.43939000368118286,
      "step": 127
    },
    {
      "epoch": 1.8106666666666666,
      "grad_norm": 0.004102814476937056,
      "learning_rate": 4.2218893451814005e-06,
      "loss": 0.4399089217185974,
      "step": 128
    },
    {
      "epoch": 1.8248888888888888,
      "grad_norm": 0.003889351151883602,
      "learning_rate": 4.140759581643386e-06,
      "loss": 0.4451609253883362,
      "step": 129
    },
    {
      "epoch": 1.8391111111111111,
      "grad_norm": 0.004501548130065203,
      "learning_rate": 4.059862272583755e-06,
      "loss": 0.4488486051559448,
      "step": 130
    },
    {
      "epoch": 1.8533333333333335,
      "grad_norm": 0.0038232814986258745,
      "learning_rate": 3.979219303543942e-06,
      "loss": 0.42662614583969116,
      "step": 131
    },
    {
      "epoch": 1.8675555555555556,
      "grad_norm": 0.003998646512627602,
      "learning_rate": 3.898852491257547e-06,
      "loss": 0.4547004997730255,
      "step": 132
    },
    {
      "epoch": 1.8817777777777778,
      "grad_norm": 0.00403416994959116,
      "learning_rate": 3.818783577748138e-06,
      "loss": 0.4510434567928314,
      "step": 133
    },
    {
      "epoch": 1.896,
      "grad_norm": 0.003799683880060911,
      "learning_rate": 3.7390342244472886e-06,
      "loss": 0.45353883504867554,
      "step": 134
    },
    {
      "epoch": 1.9102222222222223,
      "grad_norm": 0.003921311814337969,
      "learning_rate": 3.659626006334395e-06,
      "loss": 0.4302864670753479,
      "step": 135
    },
    {
      "epoch": 1.9244444444444444,
      "grad_norm": 0.00398287083953619,
      "learning_rate": 3.5805804060998926e-06,
      "loss": 0.4398406744003296,
      "step": 136
    },
    {
      "epoch": 1.9386666666666668,
      "grad_norm": 0.0037779631093144417,
      "learning_rate": 3.501918808333453e-06,
      "loss": 0.465728759765625,
      "step": 137
    },
    {
      "epoch": 1.952888888888889,
      "grad_norm": 0.003967550117522478,
      "learning_rate": 3.4236624937386874e-06,
      "loss": 0.4686010777950287,
      "step": 138
    },
    {
      "epoch": 1.967111111111111,
      "grad_norm": 0.00354909454472363,
      "learning_rate": 3.3458326333759927e-06,
      "loss": 0.43872472643852234,
      "step": 139
    },
    {
      "epoch": 1.9813333333333332,
      "grad_norm": 0.00383565342053771,
      "learning_rate": 3.268450282935026e-06,
      "loss": 0.4455334544181824,
      "step": 140
    },
    {
      "epoch": 1.9955555555555555,
      "grad_norm": 0.0037798655685037374,
      "learning_rate": 3.1915363770384223e-06,
      "loss": 0.43381941318511963,
      "step": 141
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.00621951324865222,
      "learning_rate": 3.1151117235782346e-06,
      "loss": 0.4559262990951538,
      "step": 142
    }
  ],
  "logging_steps": 1,
  "max_steps": 213,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.49085005277823e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}