{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0125,
      "grad_norm": 10.18331757027076,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.8960644006729126,
      "num_input_tokens_seen": 0,
      "step": 1
    },
    {
      "epoch": 0.025,
      "grad_norm": 9.16263025394979,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.8488595485687256,
      "num_input_tokens_seen": 0,
      "step": 2
    },
    {
      "epoch": 0.0375,
      "grad_norm": 8.92834992115862,
      "learning_rate": 3e-06,
      "loss": 0.8538516759872437,
      "num_input_tokens_seen": 0,
      "step": 3
    },
    {
      "epoch": 0.05,
      "grad_norm": 9.282181600009132,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.856260359287262,
      "num_input_tokens_seen": 0,
      "step": 4
    },
    {
      "epoch": 0.0625,
      "grad_norm": 5.998755609205955,
      "learning_rate": 5e-06,
      "loss": 0.7300517559051514,
      "num_input_tokens_seen": 0,
      "step": 5
    },
    {
      "epoch": 0.075,
      "grad_norm": 4.585755656488519,
      "learning_rate": 6e-06,
      "loss": 0.6810914278030396,
      "num_input_tokens_seen": 0,
      "step": 6
    },
    {
      "epoch": 0.0875,
      "grad_norm": 3.5581298112309763,
      "learning_rate": 7e-06,
      "loss": 0.6221330761909485,
      "num_input_tokens_seen": 0,
      "step": 7
    },
    {
      "epoch": 0.1,
      "grad_norm": 4.186415400005925,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.5942986011505127,
      "num_input_tokens_seen": 0,
      "step": 8
    },
    {
      "epoch": 0.1125,
      "grad_norm": 2.0815923930377633,
      "learning_rate": 9e-06,
      "loss": 0.5573145151138306,
      "num_input_tokens_seen": 0,
      "step": 9
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.538737138740704,
      "learning_rate": 1e-05,
      "loss": 0.5063657164573669,
      "num_input_tokens_seen": 0,
      "step": 10
    },
    {
      "epoch": 0.1375,
      "grad_norm": 1.3167709252541377,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.5080946087837219,
      "num_input_tokens_seen": 0,
      "step": 11
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.0093046488935542,
      "learning_rate": 1.2e-05,
      "loss": 0.5118667483329773,
      "num_input_tokens_seen": 0,
      "step": 12
    },
    {
      "epoch": 0.1625,
      "grad_norm": 1.0176825029370344,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.4826335608959198,
      "num_input_tokens_seen": 0,
      "step": 13
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.868692377639643,
      "learning_rate": 1.4e-05,
      "loss": 0.4561425447463989,
      "num_input_tokens_seen": 0,
      "step": 14
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.7576207830400876,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.46192091703414917,
      "num_input_tokens_seen": 0,
      "step": 15
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.6607030167581055,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.436120867729187,
      "num_input_tokens_seen": 0,
      "step": 16
    },
    {
      "epoch": 0.2125,
      "grad_norm": 0.6388324060478595,
      "learning_rate": 1.7e-05,
      "loss": 0.43788450956344604,
      "num_input_tokens_seen": 0,
      "step": 17
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.6522444786796912,
      "learning_rate": 1.8e-05,
      "loss": 0.42514723539352417,
      "num_input_tokens_seen": 0,
      "step": 18
    },
    {
      "epoch": 0.2375,
      "grad_norm": 0.5939148285210124,
      "learning_rate": 1.9e-05,
      "loss": 0.41062527894973755,
      "num_input_tokens_seen": 0,
      "step": 19
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6228429094034043,
      "learning_rate": 2e-05,
      "loss": 0.3994959890842438,
      "num_input_tokens_seen": 0,
      "step": 20
    },
    {
      "epoch": 0.2625,
      "grad_norm": 0.5940088612229671,
      "learning_rate": 1.9999658256641746e-05,
      "loss": 0.41216734051704407,
      "num_input_tokens_seen": 0,
      "step": 21
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.5920054647245636,
      "learning_rate": 1.9998633049924693e-05,
      "loss": 0.41810792684555054,
      "num_input_tokens_seen": 0,
      "step": 22
    },
    {
      "epoch": 0.2875,
      "grad_norm": 0.5480649368192407,
      "learning_rate": 1.999692444992035e-05,
      "loss": 0.4036347568035126,
      "num_input_tokens_seen": 0,
      "step": 23
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.5565757348287612,
      "learning_rate": 1.999453257340926e-05,
      "loss": 0.419705331325531,
      "num_input_tokens_seen": 0,
      "step": 24
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.5548087155409337,
      "learning_rate": 1.999145758387301e-05,
      "loss": 0.40048182010650635,
      "num_input_tokens_seen": 0,
      "step": 25
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.5338888290743757,
      "learning_rate": 1.998769969148305e-05,
      "loss": 0.40444415807724,
      "num_input_tokens_seen": 0,
      "step": 26
    },
    {
      "epoch": 0.3375,
      "grad_norm": 0.5018287159150987,
      "learning_rate": 1.9983259153086328e-05,
      "loss": 0.3908202052116394,
      "num_input_tokens_seen": 0,
      "step": 27
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.5666363779267786,
      "learning_rate": 1.9978136272187745e-05,
      "loss": 0.3917597532272339,
      "num_input_tokens_seen": 0,
      "step": 28
    },
    {
      "epoch": 0.3625,
      "grad_norm": 0.5311731782089377,
      "learning_rate": 1.997233139892941e-05,
      "loss": 0.38186532258987427,
      "num_input_tokens_seen": 0,
      "step": 29
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.5017076164418427,
      "learning_rate": 1.99658449300667e-05,
      "loss": 0.3953409492969513,
      "num_input_tokens_seen": 0,
      "step": 30
    },
    {
      "epoch": 0.3875,
      "grad_norm": 0.5191236527322374,
      "learning_rate": 1.995867730894114e-05,
      "loss": 0.3810531198978424,
      "num_input_tokens_seen": 0,
      "step": 31
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.479389601325034,
      "learning_rate": 1.9950829025450116e-05,
      "loss": 0.3787350058555603,
      "num_input_tokens_seen": 0,
      "step": 32
    },
    {
      "epoch": 0.4125,
      "grad_norm": 0.5052682473625102,
      "learning_rate": 1.9942300616013378e-05,
      "loss": 0.3784908056259155,
      "num_input_tokens_seen": 0,
      "step": 33
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.5093747529791427,
      "learning_rate": 1.9933092663536384e-05,
      "loss": 0.377264142036438,
      "num_input_tokens_seen": 0,
      "step": 34
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.5496127833092357,
      "learning_rate": 1.992320579737045e-05,
      "loss": 0.4013134837150574,
      "num_input_tokens_seen": 0,
      "step": 35
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.5194182976027281,
      "learning_rate": 1.9912640693269754e-05,
      "loss": 0.3868390917778015,
      "num_input_tokens_seen": 0,
      "step": 36
    },
    {
      "epoch": 0.4625,
      "grad_norm": 0.4772201831075947,
      "learning_rate": 1.990139807334512e-05,
      "loss": 0.3554729223251343,
      "num_input_tokens_seen": 0,
      "step": 37
    },
    {
      "epoch": 0.475,
      "grad_norm": 0.5411145901050805,
      "learning_rate": 1.9889478706014687e-05,
      "loss": 0.3768259882926941,
      "num_input_tokens_seen": 0,
      "step": 38
    },
    {
      "epoch": 0.4875,
      "grad_norm": 0.47151248168784593,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.3637596368789673,
      "num_input_tokens_seen": 0,
      "step": 39
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.4900043722490537,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 0.3731005787849426,
      "num_input_tokens_seen": 0,
      "step": 40
    },
    {
      "epoch": 0.5125,
      "grad_norm": 0.4740418320125202,
      "learning_rate": 1.984966849725452e-05,
      "loss": 0.36029529571533203,
      "num_input_tokens_seen": 0,
      "step": 41
    },
    {
      "epoch": 0.525,
      "grad_norm": 0.5282467622205699,
      "learning_rate": 1.9835050748723826e-05,
      "loss": 0.371197909116745,
      "num_input_tokens_seen": 0,
      "step": 42
    },
    {
      "epoch": 0.5375,
      "grad_norm": 0.4755646348335201,
      "learning_rate": 1.981976078753884e-05,
      "loss": 0.34178704023361206,
      "num_input_tokens_seen": 0,
      "step": 43
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.507685264776996,
      "learning_rate": 1.9803799658748096e-05,
      "loss": 0.3663065731525421,
      "num_input_tokens_seen": 0,
      "step": 44
    },
    {
      "epoch": 0.5625,
      "grad_norm": 0.5265705406067266,
      "learning_rate": 1.9787168453273546e-05,
      "loss": 0.3737153708934784,
      "num_input_tokens_seen": 0,
      "step": 45
    },
    {
      "epoch": 0.575,
      "grad_norm": 0.5571656899248943,
      "learning_rate": 1.9769868307835996e-05,
      "loss": 0.3628424406051636,
      "num_input_tokens_seen": 0,
      "step": 46
    },
    {
      "epoch": 0.5875,
      "grad_norm": 0.569279834268425,
      "learning_rate": 1.97519004048774e-05,
      "loss": 0.37988948822021484,
      "num_input_tokens_seen": 0,
      "step": 47
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4969114483932452,
      "learning_rate": 1.973326597248006e-05,
      "loss": 0.3636181950569153,
      "num_input_tokens_seen": 0,
      "step": 48
    },
    {
      "epoch": 0.6125,
      "grad_norm": 0.5439018148028109,
      "learning_rate": 1.9713966284282677e-05,
      "loss": 0.3687742352485657,
      "num_input_tokens_seen": 0,
      "step": 49
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.47096960108233016,
      "learning_rate": 1.9694002659393306e-05,
      "loss": 0.3656526207923889,
      "num_input_tokens_seen": 0,
      "step": 50
    },
    {
      "epoch": 0.6375,
      "grad_norm": 0.49069042740477836,
      "learning_rate": 1.9673376462299186e-05,
      "loss": 0.3719867467880249,
      "num_input_tokens_seen": 0,
      "step": 51
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5230240054949966,
      "learning_rate": 1.9652089102773487e-05,
      "loss": 0.3670026361942291,
      "num_input_tokens_seen": 0,
      "step": 52
    },
    {
      "epoch": 0.6625,
      "grad_norm": 0.539667408085974,
      "learning_rate": 1.963014203577896e-05,
      "loss": 0.3777502775192261,
      "num_input_tokens_seen": 0,
      "step": 53
    },
    {
      "epoch": 0.675,
      "grad_norm": 0.5303927925423055,
      "learning_rate": 1.9607536761368484e-05,
      "loss": 0.360956609249115,
      "num_input_tokens_seen": 0,
      "step": 54
    },
    {
      "epoch": 0.6875,
      "grad_norm": 0.5669762895801259,
      "learning_rate": 1.958427482458253e-05,
      "loss": 0.3712082505226135,
      "num_input_tokens_seen": 0,
      "step": 55
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.4924233132486405,
      "learning_rate": 1.9560357815343577e-05,
      "loss": 0.34069931507110596,
      "num_input_tokens_seen": 0,
      "step": 56
    },
    {
      "epoch": 0.7125,
      "grad_norm": 0.4939181685825231,
      "learning_rate": 1.9535787368347444e-05,
      "loss": 0.3445311188697815,
      "num_input_tokens_seen": 0,
      "step": 57
    },
    {
      "epoch": 0.725,
      "grad_norm": 0.5132891832051437,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 0.352506160736084,
      "num_input_tokens_seen": 0,
      "step": 58
    },
    {
      "epoch": 0.7375,
      "grad_norm": 0.5228074950046403,
      "learning_rate": 1.9484692923060095e-05,
      "loss": 0.352910578250885,
      "num_input_tokens_seen": 0,
      "step": 59
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.48331453046149664,
      "learning_rate": 1.9458172417006347e-05,
      "loss": 0.3518715500831604,
      "num_input_tokens_seen": 0,
      "step": 60
    },
    {
      "epoch": 0.7625,
      "grad_norm": 0.4971643896288794,
      "learning_rate": 1.9431005457431654e-05,
      "loss": 0.3532984256744385,
      "num_input_tokens_seen": 0,
      "step": 61
    },
    {
      "epoch": 0.775,
      "grad_norm": 0.5331008024051833,
      "learning_rate": 1.9403193901161614e-05,
      "loss": 0.3648609220981598,
      "num_input_tokens_seen": 0,
      "step": 62
    },
    {
      "epoch": 0.7875,
      "grad_norm": 1.2839239169737044,
      "learning_rate": 1.9374739649079155e-05,
      "loss": 0.3517247438430786,
      "num_input_tokens_seen": 0,
      "step": 63
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5877379242744403,
      "learning_rate": 1.934564464599461e-05,
      "loss": 0.3657301962375641,
      "num_input_tokens_seen": 0,
      "step": 64
    },
    {
      "epoch": 0.8125,
      "grad_norm": 0.4867340909281986,
      "learning_rate": 1.9315910880512792e-05,
      "loss": 0.36049771308898926,
      "num_input_tokens_seen": 0,
      "step": 65
    },
    {
      "epoch": 0.825,
      "grad_norm": 0.49356286585265735,
      "learning_rate": 1.9285540384897073e-05,
      "loss": 0.34778010845184326,
      "num_input_tokens_seen": 0,
      "step": 66
    },
    {
      "epoch": 0.8375,
      "grad_norm": 0.5535250380039742,
      "learning_rate": 1.9254535234930486e-05,
      "loss": 0.36141228675842285,
      "num_input_tokens_seen": 0,
      "step": 67
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5243933357988406,
      "learning_rate": 1.922289754977385e-05,
      "loss": 0.3524037301540375,
      "num_input_tokens_seen": 0,
      "step": 68
    },
    {
      "epoch": 0.8625,
      "grad_norm": 0.5324496372479985,
      "learning_rate": 1.919062949182091e-05,
      "loss": 0.36538389325141907,
      "num_input_tokens_seen": 0,
      "step": 69
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.49491533066436794,
      "learning_rate": 1.9157733266550577e-05,
      "loss": 0.35084018111228943,
      "num_input_tokens_seen": 0,
      "step": 70
    },
    {
      "epoch": 0.8875,
      "grad_norm": 0.5287693804586798,
      "learning_rate": 1.9124211122376138e-05,
      "loss": 0.3459678292274475,
      "num_input_tokens_seen": 0,
      "step": 71
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.4675049739386483,
      "learning_rate": 1.909006535049163e-05,
      "loss": 0.34027597308158875,
      "num_input_tokens_seen": 0,
      "step": 72
    },
    {
      "epoch": 0.9125,
      "grad_norm": 0.5068359141834208,
      "learning_rate": 1.9055298284715192e-05,
      "loss": 0.34234559535980225,
      "num_input_tokens_seen": 0,
      "step": 73
    },
    {
      "epoch": 0.925,
      "grad_norm": 0.5454693950983837,
      "learning_rate": 1.9019912301329593e-05,
      "loss": 0.3697267770767212,
      "num_input_tokens_seen": 0,
      "step": 74
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.48781498197167644,
      "learning_rate": 1.898390981891979e-05,
      "loss": 0.3399868607521057,
      "num_input_tokens_seen": 0,
      "step": 75
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.467529345150941,
      "learning_rate": 1.8947293298207637e-05,
      "loss": 0.3481365442276001,
      "num_input_tokens_seen": 0,
      "step": 76
    },
    {
      "epoch": 0.9625,
      "grad_norm": 0.5173617613436983,
      "learning_rate": 1.891006524188368e-05,
      "loss": 0.35163643956184387,
      "num_input_tokens_seen": 0,
      "step": 77
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.4964553718237553,
      "learning_rate": 1.887222819443612e-05,
      "loss": 0.3495897650718689,
      "num_input_tokens_seen": 0,
      "step": 78
    },
    {
      "epoch": 0.9875,
      "grad_norm": 0.5266061782006969,
      "learning_rate": 1.883378474197689e-05,
      "loss": 0.3525278568267822,
      "num_input_tokens_seen": 0,
      "step": 79
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.48903026352892565,
      "learning_rate": 1.879473751206489e-05,
      "loss": 0.3540067672729492,
      "num_input_tokens_seen": 0,
      "step": 80
    },
    {
      "epoch": 1.0125,
      "grad_norm": 0.8791291129207356,
      "learning_rate": 1.875508917352643e-05,
      "loss": 0.26043254137039185,
      "num_input_tokens_seen": 0,
      "step": 81
    },
    {
      "epoch": 1.025,
      "grad_norm": 0.6487054540761681,
      "learning_rate": 1.8714842436272774e-05,
      "loss": 0.2440587878227234,
      "num_input_tokens_seen": 0,
      "step": 82
    },
    {
      "epoch": 1.0375,
      "grad_norm": 0.6795282145993521,
      "learning_rate": 1.8674000051114953e-05,
      "loss": 0.2597944140434265,
      "num_input_tokens_seen": 0,
      "step": 83
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.6670449632773737,
      "learning_rate": 1.863256480957574e-05,
      "loss": 0.23764365911483765,
      "num_input_tokens_seen": 0,
      "step": 84
    },
    {
      "epoch": 1.0625,
      "grad_norm": 0.8445000033015495,
      "learning_rate": 1.8590539543698852e-05,
      "loss": 0.22128596901893616,
      "num_input_tokens_seen": 0,
      "step": 85
    },
    {
      "epoch": 1.075,
      "grad_norm": 0.7319387611539306,
      "learning_rate": 1.854792712585539e-05,
      "loss": 0.22451584041118622,
      "num_input_tokens_seen": 0,
      "step": 86
    },
    {
      "epoch": 1.0875,
      "grad_norm": 0.7347266658746741,
      "learning_rate": 1.8504730468547508e-05,
      "loss": 0.23484283685684204,
      "num_input_tokens_seen": 0,
      "step": 87
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.684429737748084,
      "learning_rate": 1.8460952524209355e-05,
      "loss": 0.22682486474514008,
      "num_input_tokens_seen": 0,
      "step": 88
    },
    {
      "epoch": 1.1125,
      "grad_norm": 0.6253196189027981,
      "learning_rate": 1.8416596285005274e-05,
      "loss": 0.23638179898262024,
      "num_input_tokens_seen": 0,
      "step": 89
    },
    {
      "epoch": 1.125,
      "grad_norm": 0.7140008070317728,
      "learning_rate": 1.8371664782625287e-05,
      "loss": 0.22379158437252045,
      "num_input_tokens_seen": 0,
      "step": 90
    },
    {
      "epoch": 1.1375,
      "grad_norm": 0.5609948172492557,
      "learning_rate": 1.8326161088077905e-05,
      "loss": 0.23043715953826904,
      "num_input_tokens_seen": 0,
      "step": 91
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.5762843622395748,
      "learning_rate": 1.8280088311480203e-05,
      "loss": 0.22419373691082,
      "num_input_tokens_seen": 0,
      "step": 92
    },
    {
      "epoch": 1.1625,
      "grad_norm": 0.7331777727867734,
      "learning_rate": 1.823344960184526e-05,
      "loss": 0.22210514545440674,
      "num_input_tokens_seen": 0,
      "step": 93
    },
    {
      "epoch": 1.175,
      "grad_norm": 0.6205497447918622,
      "learning_rate": 1.8186248146866928e-05,
      "loss": 0.23843634128570557,
      "num_input_tokens_seen": 0,
      "step": 94
    },
    {
      "epoch": 1.1875,
      "grad_norm": 0.645067422698941,
      "learning_rate": 1.813848717270195e-05,
      "loss": 0.22561757266521454,
      "num_input_tokens_seen": 0,
      "step": 95
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.5305489735340998,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.23090419173240662,
      "num_input_tokens_seen": 0,
      "step": 96
    },
    {
      "epoch": 1.2125,
      "grad_norm": 0.652421080289407,
      "learning_rate": 1.804129976242792e-05,
      "loss": 0.21994651854038239,
      "num_input_tokens_seen": 0,
      "step": 97
    },
    {
      "epoch": 1.225,
      "grad_norm": 0.546464902083412,
      "learning_rate": 1.7991879968949248e-05,
      "loss": 0.2290341556072235,
      "num_input_tokens_seen": 0,
      "step": 98
    },
    {
      "epoch": 1.2375,
      "grad_norm": 0.6476920457708351,
      "learning_rate": 1.7941913941090712e-05,
      "loss": 0.24561816453933716,
      "num_input_tokens_seen": 0,
      "step": 99
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.5782245623531915,
      "learning_rate": 1.789140509396394e-05,
      "loss": 0.23482097685337067,
      "num_input_tokens_seen": 0,
      "step": 100
    },
    {
      "epoch": 1.2625,
      "grad_norm": 0.6348611730944753,
      "learning_rate": 1.784035687978153e-05,
      "loss": 0.21998700499534607,
      "num_input_tokens_seen": 0,
      "step": 101
    },
    {
      "epoch": 1.275,
      "grad_norm": 0.5855684501933186,
      "learning_rate": 1.7788772787621126e-05,
      "loss": 0.22731050848960876,
      "num_input_tokens_seen": 0,
      "step": 102
    },
    {
      "epoch": 1.2875,
      "grad_norm": 0.5849783819104052,
      "learning_rate": 1.7736656343186897e-05,
      "loss": 0.21847045421600342,
      "num_input_tokens_seen": 0,
      "step": 103
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.6468451663174432,
      "learning_rate": 1.7684011108568593e-05,
      "loss": 0.23889131844043732,
      "num_input_tokens_seen": 0,
      "step": 104
    },
    {
      "epoch": 1.3125,
      "grad_norm": 0.5379228455435396,
      "learning_rate": 1.7630840681998068e-05,
      "loss": 0.22917379438877106,
      "num_input_tokens_seen": 0,
      "step": 105
    },
    {
      "epoch": 1.325,
      "grad_norm": 0.6386415797352409,
      "learning_rate": 1.757714869760335e-05,
      "loss": 0.22476345300674438,
      "num_input_tokens_seen": 0,
      "step": 106
    },
    {
      "epoch": 1.3375,
      "grad_norm": 0.5432607518100792,
      "learning_rate": 1.752293882516025e-05,
      "loss": 0.23026630282402039,
      "num_input_tokens_seen": 0,
      "step": 107
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.6251676560462321,
      "learning_rate": 1.7468214769841542e-05,
      "loss": 0.22793394327163696,
      "num_input_tokens_seen": 0,
      "step": 108
    },
    {
      "epoch": 1.3625,
      "grad_norm": 0.5786323989132912,
      "learning_rate": 1.7412980271963712e-05,
      "loss": 0.24610519409179688,
      "num_input_tokens_seen": 0,
      "step": 109
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.5735661628137917,
      "learning_rate": 1.735723910673132e-05,
      "loss": 0.21196551620960236,
      "num_input_tokens_seen": 0,
      "step": 110
    },
    {
      "epoch": 1.3875,
      "grad_norm": 0.5881031218701362,
      "learning_rate": 1.7300995083978965e-05,
      "loss": 0.22360339760780334,
      "num_input_tokens_seen": 0,
      "step": 111
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.5603841737931269,
      "learning_rate": 1.7244252047910893e-05,
      "loss": 0.22254161536693573,
      "num_input_tokens_seen": 0,
      "step": 112
    },
    {
      "epoch": 1.4125,
      "grad_norm": 0.566304468507664,
      "learning_rate": 1.718701387683824e-05,
      "loss": 0.21939656138420105,
      "num_input_tokens_seen": 0,
      "step": 113
    },
    {
      "epoch": 1.425,
      "grad_norm": 0.532198517126917,
      "learning_rate": 1.7129284482913973e-05,
      "loss": 0.2217104434967041,
      "num_input_tokens_seen": 0,
      "step": 114
    },
    {
      "epoch": 1.4375,
      "grad_norm": 0.5486267196897048,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.22763556241989136,
      "num_input_tokens_seen": 0,
      "step": 115
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.5318598905653756,
      "learning_rate": 1.7012367842724887e-05,
      "loss": 0.22226908802986145,
      "num_input_tokens_seen": 0,
      "step": 116
    },
    {
      "epoch": 1.4625,
      "grad_norm": 0.5219241851069808,
      "learning_rate": 1.6953188587557122e-05,
      "loss": 0.2251712530851364,
      "num_input_tokens_seen": 0,
      "step": 117
    },
    {
      "epoch": 1.475,
      "grad_norm": 0.5576204648175208,
      "learning_rate": 1.6893534091185658e-05,
      "loss": 0.2300577610731125,
      "num_input_tokens_seen": 0,
      "step": 118
    },
    {
      "epoch": 1.4875,
      "grad_norm": 0.5157156531813916,
      "learning_rate": 1.6833408430916085e-05,
      "loss": 0.23422931134700775,
      "num_input_tokens_seen": 0,
      "step": 119
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.5525368224210166,
      "learning_rate": 1.6772815716257414e-05,
      "loss": 0.23097172379493713,
      "num_input_tokens_seen": 0,
      "step": 120
    },
    {
      "epoch": 1.5125,
      "grad_norm": 0.5671209735467264,
      "learning_rate": 1.6711760088641197e-05,
      "loss": 0.22700801491737366,
      "num_input_tokens_seen": 0,
      "step": 121
    },
    {
      "epoch": 1.525,
      "grad_norm": 0.49340662518168044,
      "learning_rate": 1.6650245721138483e-05,
      "loss": 0.21679332852363586,
      "num_input_tokens_seen": 0,
      "step": 122
    },
    {
      "epoch": 1.5375,
      "grad_norm": 0.5241279113240838,
      "learning_rate": 1.658827681817458e-05,
      "loss": 0.23128211498260498,
      "num_input_tokens_seen": 0,
      "step": 123
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.5605937616757047,
      "learning_rate": 1.6525857615241686e-05,
      "loss": 0.2341003566980362,
      "num_input_tokens_seen": 0,
      "step": 124
    },
    {
      "epoch": 1.5625,
      "grad_norm": 0.5731377051701606,
      "learning_rate": 1.646299237860941e-05,
      "loss": 0.24362272024154663,
      "num_input_tokens_seen": 0,
      "step": 125
    },
    {
      "epoch": 1.575,
      "grad_norm": 0.4973323542505726,
      "learning_rate": 1.6399685405033168e-05,
      "loss": 0.21342068910598755,
      "num_input_tokens_seen": 0,
      "step": 126
    },
    {
      "epoch": 1.5875,
      "grad_norm": 0.5599176772369371,
      "learning_rate": 1.6335941021460507e-05,
      "loss": 0.2271297574043274,
      "num_input_tokens_seen": 0,
      "step": 127
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.5203662408979232,
      "learning_rate": 1.6271763584735373e-05,
      "loss": 0.22479626536369324,
      "num_input_tokens_seen": 0,
      "step": 128
    },
    {
      "epoch": 1.6125,
      "grad_norm": 0.5095863344896252,
      "learning_rate": 1.6207157481300315e-05,
      "loss": 0.22810155153274536,
      "num_input_tokens_seen": 0,
      "step": 129
    },
    {
      "epoch": 1.625,
      "grad_norm": 0.5317196453792732,
      "learning_rate": 1.6142127126896682e-05,
      "loss": 0.21053889393806458,
      "num_input_tokens_seen": 0,
      "step": 130
    },
    {
      "epoch": 1.6375,
      "grad_norm": 0.5425148287230596,
      "learning_rate": 1.6076676966262815e-05,
      "loss": 0.23062941431999207,
      "num_input_tokens_seen": 0,
      "step": 131
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.6023208751142557,
      "learning_rate": 1.6010811472830253e-05,
      "loss": 0.2463783472776413,
      "num_input_tokens_seen": 0,
      "step": 132
    },
    {
      "epoch": 1.6625,
      "grad_norm": 0.5550292129482939,
      "learning_rate": 1.5944535148417982e-05,
      "loss": 0.23075446486473083,
      "num_input_tokens_seen": 0,
      "step": 133
    },
    {
      "epoch": 1.675,
      "grad_norm": 0.5643030708792179,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 0.22998251020908356,
      "num_input_tokens_seen": 0,
      "step": 134
    },
    {
      "epoch": 1.6875,
      "grad_norm": 0.6739206936197925,
      "learning_rate": 1.5810768154019386e-05,
      "loss": 0.23184943199157715,
      "num_input_tokens_seen": 0,
      "step": 135
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.5322077543412791,
      "learning_rate": 1.5743286626829437e-05,
      "loss": 0.24749401211738586,
      "num_input_tokens_seen": 0,
      "step": 136
    },
    {
      "epoch": 1.7125,
      "grad_norm": 0.6117204460062114,
      "learning_rate": 1.5675412553627638e-05,
      "loss": 0.22619368135929108,
      "num_input_tokens_seen": 0,
      "step": 137
    },
    {
      "epoch": 1.725,
      "grad_norm": 0.5683821158495919,
      "learning_rate": 1.560715057351673e-05,
      "loss": 0.2415420114994049,
      "num_input_tokens_seen": 0,
      "step": 138
    },
    {
      "epoch": 1.7375,
      "grad_norm": 0.5531774081547891,
      "learning_rate": 1.5538505352112373e-05,
      "loss": 0.23251904547214508,
      "num_input_tokens_seen": 0,
      "step": 139
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.5656996064712688,
      "learning_rate": 1.5469481581224274e-05,
      "loss": 0.2148549109697342,
      "num_input_tokens_seen": 0,
      "step": 140
    },
    {
      "epoch": 1.7625,
      "grad_norm": 0.5342290575425301,
      "learning_rate": 1.5400083978535475e-05,
      "loss": 0.221043199300766,
      "num_input_tokens_seen": 0,
      "step": 141
    },
    {
      "epoch": 1.775,
      "grad_norm": 0.5312824045538664,
      "learning_rate": 1.533031728727994e-05,
      "loss": 0.22295251488685608,
      "num_input_tokens_seen": 0,
      "step": 142
    },
    {
      "epoch": 1.7875,
      "grad_norm": 0.5532281742783289,
      "learning_rate": 1.526018627591834e-05,
      "loss": 0.23230503499507904,
      "num_input_tokens_seen": 0,
      "step": 143
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.5486342376292719,
      "learning_rate": 1.5189695737812153e-05,
      "loss": 0.22794640064239502,
      "num_input_tokens_seen": 0,
      "step": 144
    },
    {
      "epoch": 1.8125,
      "grad_norm": 0.5282686765938053,
      "learning_rate": 1.5118850490896012e-05,
      "loss": 0.23277482390403748,
      "num_input_tokens_seen": 0,
      "step": 145
    },
    {
      "epoch": 1.825,
      "grad_norm": 0.5221771559817829,
      "learning_rate": 1.504765537734844e-05,
      "loss": 0.23067018389701843,
      "num_input_tokens_seen": 0,
      "step": 146
    },
    {
      "epoch": 1.8375,
      "grad_norm": 0.5641718599884086,
      "learning_rate": 1.4976115263260876e-05,
      "loss": 0.21835649013519287,
      "num_input_tokens_seen": 0,
      "step": 147
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.5505224831003699,
      "learning_rate": 1.4904235038305084e-05,
      "loss": 0.2256629765033722,
      "num_input_tokens_seen": 0,
      "step": 148
    },
    {
      "epoch": 1.8625,
      "grad_norm": 0.5686783195373294,
      "learning_rate": 1.4832019615398962e-05,
      "loss": 0.215658038854599,
      "num_input_tokens_seen": 0,
      "step": 149
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.5570580083339357,
      "learning_rate": 1.4759473930370738e-05,
      "loss": 0.23637929558753967,
      "num_input_tokens_seen": 0,
      "step": 150
    },
    {
      "epoch": 1.8875,
      "grad_norm": 0.5613938118868574,
      "learning_rate": 1.4686602941621618e-05,
      "loss": 0.2198466658592224,
      "num_input_tokens_seen": 0,
      "step": 151
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.5554584703399501,
      "learning_rate": 1.461341162978688e-05,
      "loss": 0.2246859222650528,
      "num_input_tokens_seen": 0,
      "step": 152
    },
    {
      "epoch": 1.9125,
      "grad_norm": 0.5909451217927424,
      "learning_rate": 1.4539904997395468e-05,
      "loss": 0.24911729991436005,
      "num_input_tokens_seen": 0,
      "step": 153
    },
    {
      "epoch": 1.925,
      "grad_norm": 0.5842777476606686,
      "learning_rate": 1.4466088068528068e-05,
      "loss": 0.23788337409496307,
      "num_input_tokens_seen": 0,
      "step": 154
    },
    {
      "epoch": 1.9375,
      "grad_norm": 0.4981326579110442,
      "learning_rate": 1.4391965888473705e-05,
      "loss": 0.2209474742412567,
      "num_input_tokens_seen": 0,
      "step": 155
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.5397167568674605,
      "learning_rate": 1.4317543523384928e-05,
      "loss": 0.23926502466201782,
      "num_input_tokens_seen": 0,
      "step": 156
    },
    {
      "epoch": 1.9625,
      "grad_norm": 0.5359703981598113,
      "learning_rate": 1.4242826059931538e-05,
      "loss": 0.2312660813331604,
      "num_input_tokens_seen": 0,
      "step": 157
    },
    {
      "epoch": 1.975,
      "grad_norm": 0.5386500827778109,
      "learning_rate": 1.4167818604952906e-05,
      "loss": 0.2199496328830719,
      "num_input_tokens_seen": 0,
      "step": 158
    },
    {
      "epoch": 1.9875,
      "grad_norm": 0.5538059936709024,
      "learning_rate": 1.409252628510894e-05,
      "loss": 0.23412078619003296,
      "num_input_tokens_seen": 0,
      "step": 159
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.540376667893175,
      "learning_rate": 1.4016954246529697e-05,
      "loss": 0.2249927967786789,
      "num_input_tokens_seen": 0,
      "step": 160
    },
    {
      "epoch": 2.0125,
      "grad_norm": 1.0198244871776765,
      "learning_rate": 1.3941107654463619e-05,
      "loss": 0.12236860394477844,
      "num_input_tokens_seen": 0,
      "step": 161
    },
    {
      "epoch": 2.025,
      "grad_norm": 0.8629260127173042,
      "learning_rate": 1.3864991692924524e-05,
      "loss": 0.11816570162773132,
      "num_input_tokens_seen": 0,
      "step": 162
    },
    {
      "epoch": 2.0375,
      "grad_norm": 0.6404376890511378,
      "learning_rate": 1.3788611564337277e-05,
      "loss": 0.10550174862146378,
      "num_input_tokens_seen": 0,
      "step": 163
    },
    {
      "epoch": 2.05,
      "grad_norm": 1.140833870667296,
      "learning_rate": 1.3711972489182208e-05,
      "loss": 0.10521072149276733,
      "num_input_tokens_seen": 0,
      "step": 164
    },
    {
      "epoch": 2.0625,
      "grad_norm": 1.004887415099318,
      "learning_rate": 1.3635079705638298e-05,
      "loss": 0.10304014384746552,
      "num_input_tokens_seen": 0,
      "step": 165
    },
    {
      "epoch": 2.075,
      "grad_norm": 0.7658325943968483,
      "learning_rate": 1.3557938469225167e-05,
      "loss": 0.10292299091815948,
      "num_input_tokens_seen": 0,
      "step": 166
    },
    {
      "epoch": 2.0875,
      "grad_norm": 0.7338849003327649,
      "learning_rate": 1.3480554052443847e-05,
      "loss": 0.10219870507717133,
      "num_input_tokens_seen": 0,
      "step": 167
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.7745676732651274,
      "learning_rate": 1.3402931744416432e-05,
      "loss": 0.10130374133586884,
      "num_input_tokens_seen": 0,
      "step": 168
    },
    {
      "epoch": 2.1125,
      "grad_norm": 0.6584333483269132,
      "learning_rate": 1.332507685052457e-05,
      "loss": 0.10410261154174805,
      "num_input_tokens_seen": 0,
      "step": 169
    },
    {
      "epoch": 2.125,
      "grad_norm": 0.6821199419154345,
      "learning_rate": 1.3246994692046837e-05,
      "loss": 0.09977763891220093,
      "num_input_tokens_seen": 0,
      "step": 170
    },
    {
      "epoch": 2.1375,
      "grad_norm": 0.6358679555892452,
      "learning_rate": 1.3168690605795044e-05,
      "loss": 0.09835107624530792,
      "num_input_tokens_seen": 0,
      "step": 171
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.6632837484026789,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.09917747974395752,
      "num_input_tokens_seen": 0,
      "step": 172
    },
    {
      "epoch": 2.1625,
      "grad_norm": 0.6342553931938368,
      "learning_rate": 1.3011438072693077e-05,
      "loss": 0.09428848326206207,
      "num_input_tokens_seen": 0,
      "step": 173
    },
    {
      "epoch": 2.175,
      "grad_norm": 0.6387577881812592,
      "learning_rate": 1.293250037384465e-05,
      "loss": 0.0958920419216156,
      "num_input_tokens_seen": 0,
      "step": 174
    },
    {
      "epoch": 2.1875,
      "grad_norm": 0.6954184373882712,
      "learning_rate": 1.2853362242491054e-05,
      "loss": 0.09917563199996948,
      "num_input_tokens_seen": 0,
      "step": 175
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.5974385656105545,
      "learning_rate": 1.2774029087618448e-05,
      "loss": 0.09344319999217987,
      "num_input_tokens_seen": 0,
      "step": 176
    },
    {
      "epoch": 2.2125,
      "grad_norm": 0.6472498757039972,
      "learning_rate": 1.269450633154258e-05,
      "loss": 0.10768131911754608,
      "num_input_tokens_seen": 0,
      "step": 177
    },
    {
      "epoch": 2.225,
      "grad_norm": 0.6685276002639324,
      "learning_rate": 1.26147994095382e-05,
      "loss": 0.10777394473552704,
      "num_input_tokens_seen": 0,
      "step": 178
    },
    {
      "epoch": 2.2375,
      "grad_norm": 0.6340976446307695,
      "learning_rate": 1.253491376946754e-05,
      "loss": 0.10363772511482239,
      "num_input_tokens_seen": 0,
      "step": 179
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.5829966761174877,
      "learning_rate": 1.2454854871407993e-05,
      "loss": 0.09860391169786453,
      "num_input_tokens_seen": 0,
      "step": 180
    },
    {
      "epoch": 2.2625,
      "grad_norm": 0.6211718617191284,
      "learning_rate": 1.2374628187278888e-05,
      "loss": 0.09785199165344238,
      "num_input_tokens_seen": 0,
      "step": 181
    },
    {
      "epoch": 2.275,
      "grad_norm": 0.5692692956767395,
      "learning_rate": 1.2294239200467516e-05,
      "loss": 0.09915725886821747,
      "num_input_tokens_seen": 0,
      "step": 182
    },
    {
      "epoch": 2.2875,
      "grad_norm": 0.6193608649665566,
      "learning_rate": 1.2213693405454345e-05,
      "loss": 0.09728467464447021,
      "num_input_tokens_seen": 0,
      "step": 183
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.6644514294612655,
      "learning_rate": 1.213299630743747e-05,
      "loss": 0.10535012185573578,
      "num_input_tokens_seen": 0,
      "step": 184
    },
    {
      "epoch": 2.3125,
      "grad_norm": 0.5826634498573604,
      "learning_rate": 1.2052153421956343e-05,
      "loss": 0.09781628847122192,
      "num_input_tokens_seen": 0,
      "step": 185
    },
    {
      "epoch": 2.325,
      "grad_norm": 0.6951420866310761,
      "learning_rate": 1.1971170274514802e-05,
      "loss": 0.09797348082065582,
      "num_input_tokens_seen": 0,
      "step": 186
    },
    {
      "epoch": 2.3375,
      "grad_norm": 0.6449424096000549,
      "learning_rate": 1.1890052400203405e-05,
      "loss": 0.11403355002403259,
      "num_input_tokens_seen": 0,
      "step": 187
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.6977055112415091,
      "learning_rate": 1.1808805343321102e-05,
      "loss": 0.09498105198144913,
      "num_input_tokens_seen": 0,
      "step": 188
    },
    {
      "epoch": 2.3625,
      "grad_norm": 0.6309628403695112,
      "learning_rate": 1.1727434656996306e-05,
      "loss": 0.0992412120103836,
      "num_input_tokens_seen": 0,
      "step": 189
    },
    {
      "epoch": 2.375,
      "grad_norm": 0.6731776940075981,
      "learning_rate": 1.164594590280734e-05,
      "loss": 0.11293548345565796,
      "num_input_tokens_seen": 0,
      "step": 190
    },
    {
      "epoch": 2.3875,
      "grad_norm": 0.6741092344709629,
      "learning_rate": 1.156434465040231e-05,
      "loss": 0.094619981944561,
      "num_input_tokens_seen": 0,
      "step": 191
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.5967386003242268,
      "learning_rate": 1.148263647711842e-05,
      "loss": 0.09347110986709595,
      "num_input_tokens_seen": 0,
      "step": 192
    },
    {
      "epoch": 2.4125,
      "grad_norm": 0.7159915413192838,
      "learning_rate": 1.140082696760078e-05,
      "loss": 0.10074266791343689,
      "num_input_tokens_seen": 0,
      "step": 193
    },
    {
      "epoch": 2.425,
      "grad_norm": 0.5968881913694516,
      "learning_rate": 1.1318921713420691e-05,
      "loss": 0.10465800762176514,
      "num_input_tokens_seen": 0,
      "step": 194
    },
    {
      "epoch": 2.4375,
      "grad_norm": 0.6589415029348668,
      "learning_rate": 1.123692631269348e-05,
      "loss": 0.10594508051872253,
      "num_input_tokens_seen": 0,
      "step": 195
    },
    {
      "epoch": 2.45,
      "grad_norm": 0.663988394877507,
      "learning_rate": 1.1154846369695864e-05,
      "loss": 0.09538954496383667,
      "num_input_tokens_seen": 0,
      "step": 196
    },
    {
      "epoch": 2.4625,
      "grad_norm": 0.6228831383495524,
      "learning_rate": 1.107268749448292e-05,
      "loss": 0.09765101969242096,
      "num_input_tokens_seen": 0,
      "step": 197
    },
    {
      "epoch": 2.475,
      "grad_norm": 0.61772733625651,
      "learning_rate": 1.099045530250463e-05,
      "loss": 0.09396866708993912,
      "num_input_tokens_seen": 0,
      "step": 198
    },
    {
      "epoch": 2.4875,
      "grad_norm": 0.5929697542542042,
      "learning_rate": 1.0908155414222083e-05,
      "loss": 0.09863300621509552,
      "num_input_tokens_seen": 0,
      "step": 199
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.6899961462901135,
      "learning_rate": 1.0825793454723325e-05,
      "loss": 0.09633656591176987,
      "num_input_tokens_seen": 0,
      "step": 200
    },
    {
      "epoch": 2.5125,
      "grad_norm": 0.5997938148312979,
      "learning_rate": 1.0743375053338879e-05,
      "loss": 0.10011985152959824,
      "num_input_tokens_seen": 0,
      "step": 201
    },
    {
      "epoch": 2.525,
      "grad_norm": 0.6332752356735514,
      "learning_rate": 1.0660905843256995e-05,
      "loss": 0.09651218354701996,
      "num_input_tokens_seen": 0,
      "step": 202
    },
    {
      "epoch": 2.5375,
      "grad_norm": 0.6204192543359215,
      "learning_rate": 1.0578391461138642e-05,
      "loss": 0.0994209498167038,
      "num_input_tokens_seen": 0,
      "step": 203
    },
    {
      "epoch": 2.55,
      "grad_norm": 0.6132942561027718,
      "learning_rate": 1.0495837546732224e-05,
      "loss": 0.10166719555854797,
      "num_input_tokens_seen": 0,
      "step": 204
    },
    {
      "epoch": 2.5625,
      "grad_norm": 0.5964143279459994,
      "learning_rate": 1.0413249742488132e-05,
      "loss": 0.10079332441091537,
      "num_input_tokens_seen": 0,
      "step": 205
    },
    {
      "epoch": 2.575,
      "grad_norm": 0.6090535510158961,
      "learning_rate": 1.0330633693173083e-05,
      "loss": 0.10682345926761627,
      "num_input_tokens_seen": 0,
      "step": 206
    },
    {
      "epoch": 2.5875,
      "grad_norm": 0.5757143060836244,
      "learning_rate": 1.0247995045484303e-05,
      "loss": 0.10448747873306274,
      "num_input_tokens_seen": 0,
      "step": 207
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.5318320587544387,
      "learning_rate": 1.0165339447663586e-05,
      "loss": 0.09677817672491074,
      "num_input_tokens_seen": 0,
      "step": 208
    },
    {
      "epoch": 2.6125,
      "grad_norm": 0.5653047610868341,
      "learning_rate": 1.008267254911125e-05,
      "loss": 0.10041716694831848,
      "num_input_tokens_seen": 0,
      "step": 209
    },
    {
      "epoch": 2.625,
      "grad_norm": 0.6709564219802151,
      "learning_rate": 1e-05,
      "loss": 0.11834404617547989,
      "num_input_tokens_seen": 0,
      "step": 210
    },
    {
      "epoch": 2.6375,
      "grad_norm": 0.59364936824183,
      "learning_rate": 9.917327450888751e-06,
      "loss": 0.10398055613040924,
      "num_input_tokens_seen": 0,
      "step": 211
    },
    {
      "epoch": 2.65,
      "grad_norm": 0.6135322123850998,
      "learning_rate": 9.834660552336415e-06,
      "loss": 0.09955007582902908,
      "num_input_tokens_seen": 0,
      "step": 212
    },
    {
      "epoch": 2.6625,
      "grad_norm": 0.5771675846362164,
      "learning_rate": 9.7520049545157e-06,
      "loss": 0.09840433299541473,
      "num_input_tokens_seen": 0,
      "step": 213
    },
    {
      "epoch": 2.675,
      "grad_norm": 0.6231353540589576,
      "learning_rate": 9.669366306826919e-06,
      "loss": 0.10380570590496063,
      "num_input_tokens_seen": 0,
      "step": 214
    },
    {
      "epoch": 2.6875,
      "grad_norm": 0.5948673639371316,
      "learning_rate": 9.586750257511868e-06,
      "loss": 0.0970538780093193,
      "num_input_tokens_seen": 0,
      "step": 215
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.6060511739998478,
      "learning_rate": 9.504162453267776e-06,
      "loss": 0.10509540140628815,
      "num_input_tokens_seen": 0,
      "step": 216
    },
    {
      "epoch": 2.7125,
      "grad_norm": 0.5510731357722317,
      "learning_rate": 9.421608538861361e-06,
      "loss": 0.09432905912399292,
      "num_input_tokens_seen": 0,
      "step": 217
    },
    {
      "epoch": 2.725,
      "grad_norm": 0.6639639280503086,
      "learning_rate": 9.339094156743007e-06,
      "loss": 0.09837593883275986,
      "num_input_tokens_seen": 0,
      "step": 218
    },
    {
      "epoch": 2.7375,
      "grad_norm": 0.6270361275419634,
      "learning_rate": 9.256624946661126e-06,
      "loss": 0.10134841501712799,
      "num_input_tokens_seen": 0,
      "step": 219
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.6771440915713338,
      "learning_rate": 9.174206545276678e-06,
      "loss": 0.11078701913356781,
      "num_input_tokens_seen": 0,
      "step": 220
    },
    {
      "epoch": 2.7625,
      "grad_norm": 0.705959945496674,
      "learning_rate": 9.091844585777919e-06,
      "loss": 0.1001749038696289,
      "num_input_tokens_seen": 0,
      "step": 221
    },
    {
      "epoch": 2.775,
      "grad_norm": 0.60937291192483,
      "learning_rate": 9.009544697495373e-06,
      "loss": 0.10557325184345245,
      "num_input_tokens_seen": 0,
      "step": 222
    },
    {
      "epoch": 2.7875,
      "grad_norm": 0.5893171675572725,
      "learning_rate": 8.927312505517086e-06,
      "loss": 0.10320694744586945,
      "num_input_tokens_seen": 0,
      "step": 223
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.6133977099413181,
      "learning_rate": 8.84515363030414e-06,
      "loss": 0.09662497788667679,
      "num_input_tokens_seen": 0,
      "step": 224
    },
    {
      "epoch": 2.8125,
      "grad_norm": 0.6010610432879008,
      "learning_rate": 8.763073687306523e-06,
      "loss": 0.10481660068035126,
      "num_input_tokens_seen": 0,
      "step": 225
    },
    {
      "epoch": 2.825,
      "grad_norm": 0.6248420832412895,
      "learning_rate": 8.68107828657931e-06,
      "loss": 0.10239937901496887,
      "num_input_tokens_seen": 0,
      "step": 226
    },
    {
      "epoch": 2.8375,
      "grad_norm": 0.5868088627329976,
      "learning_rate": 8.599173032399222e-06,
      "loss": 0.10687953978776932,
      "num_input_tokens_seen": 0,
      "step": 227
    },
    {
      "epoch": 2.85,
      "grad_norm": 0.6268898716250957,
      "learning_rate": 8.51736352288158e-06,
      "loss": 0.10268527269363403,
      "num_input_tokens_seen": 0,
      "step": 228
    },
    {
      "epoch": 2.8625,
      "grad_norm": 0.6191681347772287,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.10145796835422516,
      "num_input_tokens_seen": 0,
      "step": 229
    },
    {
      "epoch": 2.875,
      "grad_norm": 0.6058846171541453,
      "learning_rate": 8.35405409719266e-06,
      "loss": 0.104601189494133,
      "num_input_tokens_seen": 0,
      "step": 230
    },
    {
      "epoch": 2.8875,
      "grad_norm": 0.5661519092091898,
      "learning_rate": 8.2725653430037e-06,
      "loss": 0.09631498157978058,
      "num_input_tokens_seen": 0,
      "step": 231
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.5902711791447997,
      "learning_rate": 8.191194656678905e-06,
      "loss": 0.0936303585767746,
      "num_input_tokens_seen": 0,
      "step": 232
    },
    {
      "epoch": 2.9125,
      "grad_norm": 0.5638822103591541,
      "learning_rate": 8.109947599796599e-06,
      "loss": 0.1050085574388504,
      "num_input_tokens_seen": 0,
      "step": 233
    },
    {
      "epoch": 2.925,
      "grad_norm": 0.5703156532416298,
      "learning_rate": 8.0288297254852e-06,
      "loss": 0.09568509459495544,
      "num_input_tokens_seen": 0,
      "step": 234
    },
    {
      "epoch": 2.9375,
      "grad_norm": 0.6177421968590858,
      "learning_rate": 7.947846578043658e-06,
      "loss": 0.10282063484191895,
      "num_input_tokens_seen": 0,
      "step": 235
    },
    {
      "epoch": 2.95,
      "grad_norm": 0.5724279751966526,
      "learning_rate": 7.867003692562533e-06,
      "loss": 0.10039152950048447,
      "num_input_tokens_seen": 0,
      "step": 236
    },
    {
      "epoch": 2.9625,
      "grad_norm": 0.665494938328959,
      "learning_rate": 7.786306594545658e-06,
      "loss": 0.09484650194644928,
      "num_input_tokens_seen": 0,
      "step": 237
    },
    {
      "epoch": 2.975,
      "grad_norm": 0.5909403346328018,
      "learning_rate": 7.705760799532485e-06,
      "loss": 0.0970713198184967,
      "num_input_tokens_seen": 0,
      "step": 238
    },
    {
      "epoch": 2.9875,
      "grad_norm": 0.5930301687493515,
      "learning_rate": 7.625371812721115e-06,
      "loss": 0.1040472462773323,
      "num_input_tokens_seen": 0,
      "step": 239
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5975944410229318,
      "learning_rate": 7.545145128592009e-06,
      "loss": 0.10229268670082092,
      "num_input_tokens_seen": 0,
      "step": 240
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 200924346515456.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}