{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00832535486825126,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.325354868251259e-05,
      "grad_norm": 0.021569252014160156,
      "learning_rate": 1e-05,
      "loss": 10.3794,
      "step": 1
    },
    {
      "epoch": 8.325354868251259e-05,
      "eval_loss": 10.377388000488281,
      "eval_runtime": 160.0598,
      "eval_samples_per_second": 63.195,
      "eval_steps_per_second": 7.903,
      "step": 1
    },
    {
      "epoch": 0.00016650709736502518,
      "grad_norm": 0.03107944317162037,
      "learning_rate": 2e-05,
      "loss": 10.3791,
      "step": 2
    },
    {
      "epoch": 0.00024976064604753775,
      "grad_norm": 0.02209843136370182,
      "learning_rate": 3e-05,
      "loss": 10.3773,
      "step": 3
    },
    {
      "epoch": 0.00033301419473005036,
      "grad_norm": 0.02121385745704174,
      "learning_rate": 4e-05,
      "loss": 10.3788,
      "step": 4
    },
    {
      "epoch": 0.00041626774341256296,
      "grad_norm": 0.019519681110978127,
      "learning_rate": 5e-05,
      "loss": 10.3763,
      "step": 5
    },
    {
      "epoch": 0.0004995212920950755,
      "grad_norm": 0.022146768867969513,
      "learning_rate": 6e-05,
      "loss": 10.3804,
      "step": 6
    },
    {
      "epoch": 0.0005827748407775882,
      "grad_norm": 0.024616023525595665,
      "learning_rate": 7e-05,
      "loss": 10.3777,
      "step": 7
    },
    {
      "epoch": 0.0006660283894601007,
      "grad_norm": 0.02391134202480316,
      "learning_rate": 8e-05,
      "loss": 10.3806,
      "step": 8
    },
    {
      "epoch": 0.0007492819381426134,
      "grad_norm": 0.0267960112541914,
      "learning_rate": 9e-05,
      "loss": 10.3777,
      "step": 9
    },
    {
      "epoch": 0.0007492819381426134,
      "eval_loss": 10.377134323120117,
      "eval_runtime": 160.2613,
      "eval_samples_per_second": 63.116,
      "eval_steps_per_second": 7.893,
      "step": 9
    },
    {
      "epoch": 0.0008325354868251259,
      "grad_norm": 0.02298792079091072,
      "learning_rate": 0.0001,
      "loss": 10.3777,
      "step": 10
    },
    {
      "epoch": 0.0009157890355076385,
      "grad_norm": 0.025504613295197487,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3774,
      "step": 11
    },
    {
      "epoch": 0.000999042584190151,
      "grad_norm": 0.027433175593614578,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3788,
      "step": 12
    },
    {
      "epoch": 0.0010822961328726638,
      "grad_norm": 0.02382979728281498,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3777,
      "step": 13
    },
    {
      "epoch": 0.0011655496815551763,
      "grad_norm": 0.023936374112963676,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3797,
      "step": 14
    },
    {
      "epoch": 0.0012488032302376889,
      "grad_norm": 0.02442743629217148,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3778,
      "step": 15
    },
    {
      "epoch": 0.0013320567789202014,
      "grad_norm": 0.019230961799621582,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3759,
      "step": 16
    },
    {
      "epoch": 0.001415310327602714,
      "grad_norm": 0.022421833127737045,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3766,
      "step": 17
    },
    {
      "epoch": 0.0014985638762852267,
      "grad_norm": 0.02025768905878067,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3755,
      "step": 18
    },
    {
      "epoch": 0.0014985638762852267,
      "eval_loss": 10.376496315002441,
      "eval_runtime": 159.6247,
      "eval_samples_per_second": 63.367,
      "eval_steps_per_second": 7.925,
      "step": 18
    },
    {
      "epoch": 0.0015818174249677393,
      "grad_norm": 0.024560928344726562,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3762,
      "step": 19
    },
    {
      "epoch": 0.0016650709736502518,
      "grad_norm": 0.02397759258747101,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3746,
      "step": 20
    },
    {
      "epoch": 0.0017483245223327644,
      "grad_norm": 0.02246921882033348,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3755,
      "step": 21
    },
    {
      "epoch": 0.001831578071015277,
      "grad_norm": 0.02009345218539238,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3756,
      "step": 22
    },
    {
      "epoch": 0.0019148316196977897,
      "grad_norm": 0.022839196026325226,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3727,
      "step": 23
    },
    {
      "epoch": 0.001998085168380302,
      "grad_norm": 0.02412959560751915,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3778,
      "step": 24
    },
    {
      "epoch": 0.002081338717062815,
      "grad_norm": 0.027805138379335403,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3754,
      "step": 25
    },
    {
      "epoch": 0.0021645922657453276,
      "grad_norm": 0.025182532146573067,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3756,
      "step": 26
    },
    {
      "epoch": 0.00224784581442784,
      "grad_norm": 0.025572553277015686,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3756,
      "step": 27
    },
    {
      "epoch": 0.00224784581442784,
      "eval_loss": 10.375847816467285,
      "eval_runtime": 149.4247,
      "eval_samples_per_second": 67.693,
      "eval_steps_per_second": 8.466,
      "step": 27
    },
    {
      "epoch": 0.0023310993631103527,
      "grad_norm": 0.023483281955122948,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3749,
      "step": 28
    },
    {
      "epoch": 0.002414352911792865,
      "grad_norm": 0.023586202412843704,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3769,
      "step": 29
    },
    {
      "epoch": 0.0024976064604753778,
      "grad_norm": 0.019847828894853592,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3747,
      "step": 30
    },
    {
      "epoch": 0.0025808600091578905,
      "grad_norm": 0.02112536132335663,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3752,
      "step": 31
    },
    {
      "epoch": 0.002664113557840403,
      "grad_norm": 0.020234240218997,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3743,
      "step": 32
    },
    {
      "epoch": 0.0027473671065229156,
      "grad_norm": 0.022708367556333542,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3754,
      "step": 33
    },
    {
      "epoch": 0.002830620655205428,
      "grad_norm": 0.02386791631579399,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3728,
      "step": 34
    },
    {
      "epoch": 0.0029138742038879407,
      "grad_norm": 0.02285214513540268,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3765,
      "step": 35
    },
    {
      "epoch": 0.0029971277525704535,
      "grad_norm": 0.023896262049674988,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3748,
      "step": 36
    },
    {
      "epoch": 0.0029971277525704535,
      "eval_loss": 10.375186920166016,
      "eval_runtime": 148.5988,
      "eval_samples_per_second": 68.069,
      "eval_steps_per_second": 8.513,
      "step": 36
    },
    {
      "epoch": 0.003080381301252966,
      "grad_norm": 0.025179745629429817,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.376,
      "step": 37
    },
    {
      "epoch": 0.0031636348499354786,
      "grad_norm": 0.026716183871030807,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3766,
      "step": 38
    },
    {
      "epoch": 0.003246888398617991,
      "grad_norm": 0.030639372766017914,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3764,
      "step": 39
    },
    {
      "epoch": 0.0033301419473005037,
      "grad_norm": 0.02914862520992756,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3735,
      "step": 40
    },
    {
      "epoch": 0.0034133954959830164,
      "grad_norm": 0.022033508867025375,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3769,
      "step": 41
    },
    {
      "epoch": 0.0034966490446655288,
      "grad_norm": 0.02572484128177166,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3752,
      "step": 42
    },
    {
      "epoch": 0.0035799025933480415,
      "grad_norm": 0.023432254791259766,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3747,
      "step": 43
    },
    {
      "epoch": 0.003663156142030554,
      "grad_norm": 0.029329584911465645,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3749,
      "step": 44
    },
    {
      "epoch": 0.0037464096907130666,
      "grad_norm": 0.027913155034184456,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.374,
      "step": 45
    },
    {
      "epoch": 0.0037464096907130666,
      "eval_loss": 10.374531745910645,
      "eval_runtime": 148.61,
      "eval_samples_per_second": 68.064,
      "eval_steps_per_second": 8.512,
      "step": 45
    },
    {
      "epoch": 0.0038296632393955794,
      "grad_norm": 0.023554999381303787,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3721,
      "step": 46
    },
    {
      "epoch": 0.003912916788078092,
      "grad_norm": 0.03028443641960621,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3751,
      "step": 47
    },
    {
      "epoch": 0.003996170336760604,
      "grad_norm": 0.02735976316034794,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3768,
      "step": 48
    },
    {
      "epoch": 0.004079423885443117,
      "grad_norm": 0.027595043182373047,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3733,
      "step": 49
    },
    {
      "epoch": 0.00416267743412563,
      "grad_norm": 0.02975800819694996,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3733,
      "step": 50
    },
    {
      "epoch": 0.004245930982808142,
      "grad_norm": 0.022592192515730858,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3757,
      "step": 51
    },
    {
      "epoch": 0.004329184531490655,
      "grad_norm": 0.02746448665857315,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.373,
      "step": 52
    },
    {
      "epoch": 0.004412438080173167,
      "grad_norm": 0.034864962100982666,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3755,
      "step": 53
    },
    {
      "epoch": 0.00449569162885568,
      "grad_norm": 0.02986881136894226,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3741,
      "step": 54
    },
    {
      "epoch": 0.00449569162885568,
      "eval_loss": 10.373912811279297,
      "eval_runtime": 148.6352,
      "eval_samples_per_second": 68.053,
      "eval_steps_per_second": 8.511,
      "step": 54
    },
    {
      "epoch": 0.0045789451775381925,
      "grad_norm": 0.032523926347494125,
      "learning_rate": 5e-05,
      "loss": 10.3756,
      "step": 55
    },
    {
      "epoch": 0.004662198726220705,
      "grad_norm": 0.029269371181726456,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3737,
      "step": 56
    },
    {
      "epoch": 0.004745452274903218,
      "grad_norm": 0.02924845553934574,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3736,
      "step": 57
    },
    {
      "epoch": 0.00482870582358573,
      "grad_norm": 0.028468172997236252,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3716,
      "step": 58
    },
    {
      "epoch": 0.004911959372268243,
      "grad_norm": 0.02863762155175209,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3734,
      "step": 59
    },
    {
      "epoch": 0.0049952129209507555,
      "grad_norm": 0.03285225108265877,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3724,
      "step": 60
    },
    {
      "epoch": 0.005078466469633268,
      "grad_norm": 0.028849463909864426,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3711,
      "step": 61
    },
    {
      "epoch": 0.005161720018315781,
      "grad_norm": 0.03323189169168472,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3739,
      "step": 62
    },
    {
      "epoch": 0.005244973566998293,
      "grad_norm": 0.03293667733669281,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3728,
      "step": 63
    },
    {
      "epoch": 0.005244973566998293,
      "eval_loss": 10.373388290405273,
      "eval_runtime": 148.6153,
      "eval_samples_per_second": 68.062,
      "eval_steps_per_second": 8.512,
      "step": 63
    },
    {
      "epoch": 0.005328227115680806,
      "grad_norm": 0.03562981262803078,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3694,
      "step": 64
    },
    {
      "epoch": 0.0054114806643633185,
      "grad_norm": 0.02975441701710224,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3768,
      "step": 65
    },
    {
      "epoch": 0.005494734213045831,
      "grad_norm": 0.04472412168979645,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3748,
      "step": 66
    },
    {
      "epoch": 0.005577987761728344,
      "grad_norm": 0.030767936259508133,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3734,
      "step": 67
    },
    {
      "epoch": 0.005661241310410856,
      "grad_norm": 0.030225660651922226,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3752,
      "step": 68
    },
    {
      "epoch": 0.005744494859093369,
      "grad_norm": 0.039484333246946335,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.373,
      "step": 69
    },
    {
      "epoch": 0.005827748407775881,
      "grad_norm": 0.03261690214276314,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3731,
      "step": 70
    },
    {
      "epoch": 0.005911001956458394,
      "grad_norm": 0.03445957973599434,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3739,
      "step": 71
    },
    {
      "epoch": 0.005994255505140907,
      "grad_norm": 0.03545086085796356,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3708,
      "step": 72
    },
    {
      "epoch": 0.005994255505140907,
      "eval_loss": 10.372991561889648,
      "eval_runtime": 148.5888,
      "eval_samples_per_second": 68.074,
      "eval_steps_per_second": 8.513,
      "step": 72
    },
    {
      "epoch": 0.006077509053823419,
      "grad_norm": 0.039018601179122925,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3709,
      "step": 73
    },
    {
      "epoch": 0.006160762602505932,
      "grad_norm": 0.03845333680510521,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3735,
      "step": 74
    },
    {
      "epoch": 0.006244016151188444,
      "grad_norm": 0.029868410900235176,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.373,
      "step": 75
    },
    {
      "epoch": 0.006327269699870957,
      "grad_norm": 0.03503395617008209,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3724,
      "step": 76
    },
    {
      "epoch": 0.00641052324855347,
      "grad_norm": 0.04458336532115936,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3728,
      "step": 77
    },
    {
      "epoch": 0.006493776797235982,
      "grad_norm": 0.03825473040342331,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3736,
      "step": 78
    },
    {
      "epoch": 0.006577030345918495,
      "grad_norm": 0.03983627259731293,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3732,
      "step": 79
    },
    {
      "epoch": 0.006660283894601007,
      "grad_norm": 0.035727862268686295,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3727,
      "step": 80
    },
    {
      "epoch": 0.00674353744328352,
      "grad_norm": 0.04354983568191528,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3733,
      "step": 81
    },
    {
      "epoch": 0.00674353744328352,
      "eval_loss": 10.372751235961914,
      "eval_runtime": 148.4839,
      "eval_samples_per_second": 68.122,
      "eval_steps_per_second": 8.519,
      "step": 81
    },
    {
      "epoch": 0.006826790991966033,
      "grad_norm": 0.033028386533260345,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3693,
      "step": 82
    },
    {
      "epoch": 0.006910044540648545,
      "grad_norm": 0.03836917132139206,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3715,
      "step": 83
    },
    {
      "epoch": 0.0069932980893310575,
      "grad_norm": 0.036879587918519974,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3762,
      "step": 84
    },
    {
      "epoch": 0.00707655163801357,
      "grad_norm": 0.03589490056037903,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3707,
      "step": 85
    },
    {
      "epoch": 0.007159805186696083,
      "grad_norm": 0.03812255710363388,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3741,
      "step": 86
    },
    {
      "epoch": 0.007243058735378596,
      "grad_norm": 0.041089076548814774,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3723,
      "step": 87
    },
    {
      "epoch": 0.007326312284061108,
      "grad_norm": 0.03632598742842674,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3768,
      "step": 88
    },
    {
      "epoch": 0.0074095658327436205,
      "grad_norm": 0.03819997236132622,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.369,
      "step": 89
    },
    {
      "epoch": 0.007492819381426133,
      "grad_norm": 0.0333368182182312,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3696,
      "step": 90
    },
    {
      "epoch": 0.007492819381426133,
      "eval_loss": 10.372652053833008,
      "eval_runtime": 148.6025,
      "eval_samples_per_second": 68.067,
      "eval_steps_per_second": 8.513,
      "step": 90
    },
    {
      "epoch": 0.007576072930108646,
      "grad_norm": 0.03456645831465721,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3723,
      "step": 91
    },
    {
      "epoch": 0.007659326478791159,
      "grad_norm": 0.04168243333697319,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3738,
      "step": 92
    },
    {
      "epoch": 0.007742580027473671,
      "grad_norm": 0.03744868189096451,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.372,
      "step": 93
    },
    {
      "epoch": 0.007825833576156184,
      "grad_norm": 0.03732309117913246,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3731,
      "step": 94
    },
    {
      "epoch": 0.007909087124838697,
      "grad_norm": 0.031954191625118256,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3735,
      "step": 95
    },
    {
      "epoch": 0.007992340673521208,
      "grad_norm": 0.0394279770553112,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3702,
      "step": 96
    },
    {
      "epoch": 0.008075594222203721,
      "grad_norm": 0.04486799240112305,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3759,
      "step": 97
    },
    {
      "epoch": 0.008158847770886234,
      "grad_norm": 0.037964317947626114,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.373,
      "step": 98
    },
    {
      "epoch": 0.008242101319568746,
      "grad_norm": 0.03853140026330948,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3717,
      "step": 99
    },
    {
      "epoch": 0.008242101319568746,
      "eval_loss": 10.372636795043945,
      "eval_runtime": 148.5867,
      "eval_samples_per_second": 68.075,
      "eval_steps_per_second": 8.514,
      "step": 99
    },
    {
      "epoch": 0.00832535486825126,
      "grad_norm": 0.030309082940220833,
      "learning_rate": 0.0,
      "loss": 10.3732,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 10460489318400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}