{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.09770395701025891,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004885197850512946,
      "grad_norm": 0.00014923018170520663,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0004885197850512946,
      "eval_loss": 11.5,
      "eval_runtime": 21.8085,
      "eval_samples_per_second": 158.103,
      "eval_steps_per_second": 79.052,
      "step": 1
    },
    {
      "epoch": 0.0009770395701025891,
      "grad_norm": 0.00010189843305852264,
      "learning_rate": 6.666666666666667e-06,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0014655593551538837,
      "grad_norm": 0.00011581017315620556,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0019540791402051783,
      "grad_norm": 9.342029079562053e-05,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.002442598925256473,
      "grad_norm": 0.0001268885243916884,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0029311187103077674,
      "grad_norm": 0.0001576822978677228,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.003419638495359062,
      "grad_norm": 0.00015863515727687627,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0039081582804103565,
      "grad_norm": 0.00016007298836484551,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.004396678065461651,
      "grad_norm": 0.00016516570758540183,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.004885197850512946,
      "grad_norm": 0.00019161883392371237,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.00537371763556424,
      "grad_norm": 0.00019221696129534394,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.005862237420615535,
      "grad_norm": 0.00019196397624909878,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.006350757205666829,
      "grad_norm": 0.00018356094369664788,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.006839276990718124,
      "grad_norm": 0.0001760963787091896,
      "learning_rate": 4.666666666666667e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.0073277967757694185,
      "grad_norm": 0.0001812873815651983,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.007816316560820713,
      "grad_norm": 0.00020668996148742735,
      "learning_rate": 5.333333333333333e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.008304836345872008,
      "grad_norm": 0.0001919849164551124,
      "learning_rate": 5.666666666666667e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.008793356130923302,
      "grad_norm": 0.00018678826745599508,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.009281875915974597,
      "grad_norm": 0.00017623617895878851,
      "learning_rate": 6.333333333333333e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.009770395701025891,
      "grad_norm": 0.00020370143465697765,
      "learning_rate": 6.666666666666667e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.010258915486077186,
      "grad_norm": 0.0001907388650579378,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.01074743527112848,
      "grad_norm": 0.00018769825692288578,
      "learning_rate": 7.333333333333333e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.011235955056179775,
      "grad_norm": 0.00017153348017018288,
      "learning_rate": 7.666666666666667e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.01172447484123107,
      "grad_norm": 0.00022031365369912237,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.012212994626282364,
      "grad_norm": 0.0002413343609077856,
      "learning_rate": 8.333333333333334e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.012701514411333659,
      "grad_norm": 0.0002299462357768789,
      "learning_rate": 8.666666666666667e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.013190034196384953,
      "grad_norm": 0.0002480004623066634,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.013678553981436248,
      "grad_norm": 0.0002981836150866002,
      "learning_rate": 9.333333333333334e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.014167073766487542,
      "grad_norm": 0.0003038592985831201,
      "learning_rate": 9.666666666666667e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.014655593551538837,
      "grad_norm": 0.00028463880880735815,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.015144113336590131,
      "grad_norm": 0.00029816399910487235,
      "learning_rate": 9.999146252290264e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.015632633121641426,
      "grad_norm": 0.00033598695881664753,
      "learning_rate": 9.996585300715116e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.01612115290669272,
      "grad_norm": 0.0003494895063340664,
      "learning_rate": 9.99231801983717e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.016609672691744015,
      "grad_norm": 0.0003391339269001037,
      "learning_rate": 9.986345866928941e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.01709819247679531,
      "grad_norm": 0.0003875583643093705,
      "learning_rate": 9.978670881475172e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.017586712261846604,
      "grad_norm": 0.00042881048284471035,
      "learning_rate": 9.96929568447637e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.0180752320468979,
      "grad_norm": 0.0004535310436040163,
      "learning_rate": 9.958223477553714e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.018563751831949193,
      "grad_norm": 0.0004276837280485779,
      "learning_rate": 9.94545804185573e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.019052271617000488,
      "grad_norm": 0.0004478572809603065,
      "learning_rate": 9.931003736767013e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.019540791402051783,
      "grad_norm": 0.0004176196234766394,
      "learning_rate": 9.91486549841951e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.020029311187103077,
      "grad_norm": 0.0005269350949674845,
      "learning_rate": 9.89704883800683e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.02051783097215437,
      "grad_norm": 0.0005566150066442788,
      "learning_rate": 9.877559839902184e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.021006350757205666,
      "grad_norm": 0.0005373305757530034,
      "learning_rate": 9.85640515958057e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.02149487054225696,
      "grad_norm": 0.0006445915205404162,
      "learning_rate": 9.833592021345937e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.021983390327308255,
      "grad_norm": 0.0006316164508461952,
      "learning_rate": 9.809128215864097e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.02247191011235955,
      "grad_norm": 0.0006566172814927995,
      "learning_rate": 9.783022097502204e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.022960429897410845,
      "grad_norm": 0.000673891045153141,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.02344894968246214,
      "grad_norm": 0.0007460052729584277,
      "learning_rate": 9.725919140804099e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.023937469467513434,
      "grad_norm": 0.0008335084421560168,
      "learning_rate": 9.694941803075283e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.024425989252564728,
      "grad_norm": 0.0007683219737373292,
      "learning_rate": 9.662361147021779e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.024425989252564728,
      "eval_loss": 11.5,
      "eval_runtime": 21.8811,
      "eval_samples_per_second": 157.579,
      "eval_steps_per_second": 78.79,
      "step": 50
    },
    {
      "epoch": 0.024914509037616023,
      "grad_norm": 0.0005438526277430356,
      "learning_rate": 9.628188298907782e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.025403028822667317,
      "grad_norm": 0.000465790944872424,
      "learning_rate": 9.592434928729616e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.025891548607718612,
      "grad_norm": 0.0005006449646316469,
      "learning_rate": 9.555113246230442e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.026380068392769906,
      "grad_norm": 0.0004962133825756609,
      "learning_rate": 9.516235996730645e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.0268685881778212,
      "grad_norm": 0.0005621546879410744,
      "learning_rate": 9.475816456775313e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.027357107962872496,
      "grad_norm": 0.0008538339752703905,
      "learning_rate": 9.43386842960031e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.02784562774792379,
      "grad_norm": 0.0008000246016308665,
      "learning_rate": 9.39040624041849e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.028334147532975085,
      "grad_norm": 0.0008223172626458108,
      "learning_rate": 9.345444731527642e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.02882266731802638,
      "grad_norm": 0.0008595731924287975,
      "learning_rate": 9.298999257241863e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.029311187103077674,
      "grad_norm": 0.0009680544608272612,
      "learning_rate": 9.251085678648072e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.02979970688812897,
      "grad_norm": 0.0008582666050642729,
      "learning_rate": 9.201720358189464e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.030288226673180263,
      "grad_norm": 0.0009988963138312101,
      "learning_rate": 9.150920154077754e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.030776746458231558,
      "grad_norm": 0.0010351977543905377,
      "learning_rate": 9.098702414536107e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.03126526624328285,
      "grad_norm": 0.000999148585833609,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.03175378602833415,
      "grad_norm": 0.0010952550219371915,
      "learning_rate": 8.9900861364012e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.03224230581338544,
      "grad_norm": 0.001108844648115337,
      "learning_rate": 8.933724690167417e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.032730825598436736,
      "grad_norm": 0.0010663546854630113,
      "learning_rate": 8.876019880555649e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.03321934538348803,
      "grad_norm": 0.0011809360003098845,
      "learning_rate": 8.816991413705516e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.033707865168539325,
      "grad_norm": 0.00114791642408818,
      "learning_rate": 8.756659447784368e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.03419638495359062,
      "grad_norm": 0.001080791698768735,
      "learning_rate": 8.695044586103296e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.034684904738641914,
      "grad_norm": 0.0010704582091420889,
      "learning_rate": 8.632167870081121e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.03517342452369321,
      "grad_norm": 0.0011543328873813152,
      "learning_rate": 8.568050772058762e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.0356619443087445,
      "grad_norm": 0.0013566854177042842,
      "learning_rate": 8.502715187966455e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.0361504640937958,
      "grad_norm": 0.0013899672776460648,
      "learning_rate": 8.436183429846313e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.03663898387884709,
      "grad_norm": 0.0013129275757819414,
      "learning_rate": 8.368478218232787e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.03712750366389839,
      "grad_norm": 0.0012440407881513238,
      "learning_rate": 8.299622674393614e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.03761602344894968,
      "grad_norm": 0.0013878497993573546,
      "learning_rate": 8.229640312433937e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.038104543234000976,
      "grad_norm": 0.0014280028408393264,
      "learning_rate": 8.158555031266254e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.03859306301905227,
      "grad_norm": 0.001614846638403833,
      "learning_rate": 8.086391106448965e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.039081582804103565,
      "grad_norm": 0.0015674001770094037,
      "learning_rate": 8.013173181896283e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.03957010258915486,
      "grad_norm": 0.001519041950814426,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.040058622374206154,
      "grad_norm": 0.0017371849389746785,
      "learning_rate": 7.863675700402526e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.04054714215925745,
      "grad_norm": 0.0015264844987541437,
      "learning_rate": 7.787447196714427e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.04103566194430874,
      "grad_norm": 0.0015574233839288354,
      "learning_rate": 7.710266782362247e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.04152418172936004,
      "grad_norm": 0.0017922529950737953,
      "learning_rate": 7.63216081438678e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.04201270151441133,
      "grad_norm": 0.0015132039552554488,
      "learning_rate": 7.553155965904535e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.04250122129946263,
      "grad_norm": 0.0014118703547865152,
      "learning_rate": 7.473279216998895e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.04298974108451392,
      "grad_norm": 0.0015360661782324314,
      "learning_rate": 7.392557845506432e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 0.0016589147271588445,
      "learning_rate": 7.311019417701566e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.04396678065461651,
      "grad_norm": 0.0018973118858411908,
      "learning_rate": 7.228691778882693e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.044455300439667805,
      "grad_norm": 0.0018632501596584916,
      "learning_rate": 7.145603043863045e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.0449438202247191,
      "grad_norm": 0.0018421127460896969,
      "learning_rate": 7.061781587369519e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.045432340009770394,
      "grad_norm": 0.001867462880909443,
      "learning_rate": 6.977256034352712e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.04592085979482169,
      "grad_norm": 0.0016661660047248006,
      "learning_rate": 6.892055250211552e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.046409379579872984,
      "grad_norm": 0.0020030655432492495,
      "learning_rate": 6.806208330935766e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.04689789936492428,
      "grad_norm": 0.0022019976750016212,
      "learning_rate": 6.719744593169641e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.04738641914997557,
      "grad_norm": 0.0023582875728607178,
      "learning_rate": 6.632693564200416e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.04787493893502687,
      "grad_norm": 0.0020912224426865578,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.04836345872007816,
      "grad_norm": 0.0023314449936151505,
      "learning_rate": 6.456948734446624e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.048851978505129456,
      "grad_norm": 0.002223197603598237,
      "learning_rate": 6.368314950360415e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.048851978505129456,
      "eval_loss": 11.5,
      "eval_runtime": 21.7472,
      "eval_samples_per_second": 158.549,
      "eval_steps_per_second": 79.275,
      "step": 100
    },
    {
      "epoch": 0.04934049829018075,
      "grad_norm": 0.0019651062320917845,
      "learning_rate": 6.279213887972179e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.049829018075232046,
      "grad_norm": 0.0010920295026153326,
      "learning_rate": 6.189675975213094e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.05031753786028334,
      "grad_norm": 0.001620462746359408,
      "learning_rate": 6.099731789198344e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.050806057645334635,
      "grad_norm": 0.0015201811911538243,
      "learning_rate": 6.009412045785051e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.05129457743038593,
      "grad_norm": 0.0017807093681767583,
      "learning_rate": 5.918747589082853e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.051783097215437224,
      "grad_norm": 0.0019678312819451094,
      "learning_rate": 5.82776938092065e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.05227161700048852,
      "grad_norm": 0.0021614041179418564,
      "learning_rate": 5.736508490273188e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.05276013678553981,
      "grad_norm": 0.00198457227088511,
      "learning_rate": 5.644996082651017e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.05324865657059111,
      "grad_norm": 0.001815136638469994,
      "learning_rate": 5.553263409457504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.0537371763556424,
      "grad_norm": 0.0023733500856906176,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.0542256961406937,
      "grad_norm": 0.0020339249167591333,
      "learning_rate": 5.3692626373743706e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.05471421592574499,
      "grad_norm": 0.002384207909926772,
      "learning_rate": 5.27705737457985e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.055202735710796286,
      "grad_norm": 0.0023456341587007046,
      "learning_rate": 5.184757496945726e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.05569125549584758,
      "grad_norm": 0.002359037986025214,
      "learning_rate": 5.092394524795649e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.056179775280898875,
      "grad_norm": 0.0022823396138846874,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.05666829506595017,
      "grad_norm": 0.002569975098595023,
      "learning_rate": 4.907605475204352e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.057156814851001464,
      "grad_norm": 0.0023908009752631187,
      "learning_rate": 4.8152425030542766e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.05764533463605276,
      "grad_norm": 0.002633164869621396,
      "learning_rate": 4.72294262542015e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.05813385442110405,
      "grad_norm": 0.0026206020265817642,
      "learning_rate": 4.6307373626256306e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.05862237420615535,
      "grad_norm": 0.002555572660639882,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.05911089399120664,
      "grad_norm": 0.0024891262874007225,
      "learning_rate": 4.446736590542497e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.05959941377625794,
      "grad_norm": 0.002794750966131687,
      "learning_rate": 4.3550039173489845e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.06008793356130923,
      "grad_norm": 0.002416015602648258,
      "learning_rate": 4.2634915097268115e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.060576453346360526,
      "grad_norm": 0.0028717226814478636,
      "learning_rate": 4.1722306190793495e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.06106497313141182,
      "grad_norm": 0.00271116872318089,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.061553492916463115,
      "grad_norm": 0.0025964034721255302,
      "learning_rate": 3.99058795421495e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.06204201270151441,
      "grad_norm": 0.002626827685162425,
      "learning_rate": 3.9002682108016585e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.0625305324865657,
      "grad_norm": 0.002837597858160734,
      "learning_rate": 3.8103240247869075e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.063019052271617,
      "grad_norm": 0.0029369723051786423,
      "learning_rate": 3.720786112027822e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.0635075720566683,
      "grad_norm": 0.003107696305960417,
      "learning_rate": 3.631685049639586e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.06399609184171959,
      "grad_norm": 0.003282048273831606,
      "learning_rate": 3.543051265553377e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.06448461162677088,
      "grad_norm": 0.003092048689723015,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.06497313141182218,
      "grad_norm": 0.002742452546954155,
      "learning_rate": 3.367306435799584e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.06546165119687347,
      "grad_norm": 0.002884424291551113,
      "learning_rate": 3.2802554068303596e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.06595017098192477,
      "grad_norm": 0.003205804852768779,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.06643869076697606,
      "grad_norm": 0.0032421215437352657,
      "learning_rate": 3.107944749788449e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.06692721055202736,
      "grad_norm": 0.002821906702592969,
      "learning_rate": 3.0227439656472877e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.06741573033707865,
      "grad_norm": 0.0034650960005819798,
      "learning_rate": 2.9382184126304834e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.06790425012212994,
      "grad_norm": 0.0033117257989943027,
      "learning_rate": 2.8543969561369556e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.06839276990718124,
      "grad_norm": 0.0030436816159635782,
      "learning_rate": 2.771308221117309e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.06888128969223253,
      "grad_norm": 0.0032486796844750643,
      "learning_rate": 2.688980582298435e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.06936980947728383,
      "grad_norm": 0.003315830836072564,
      "learning_rate": 2.607442154493568e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.06985832926233512,
      "grad_norm": 0.0029912549071013927,
      "learning_rate": 2.5267207830011068e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.07034684904738642,
      "grad_norm": 0.003400547197088599,
      "learning_rate": 2.446844034095466e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.07083536883243771,
      "grad_norm": 0.0037027092184871435,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.071323888617489,
      "grad_norm": 0.0033600705210119486,
      "learning_rate": 2.2897332176377528e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.0718124084025403,
      "grad_norm": 0.0032807497773319483,
      "learning_rate": 2.2125528032855724e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.0723009281875916,
      "grad_norm": 0.0033261869102716446,
      "learning_rate": 2.136324299597474e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.07278944797264289,
      "grad_norm": 0.004576267208904028,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.07327796775769418,
      "grad_norm": 0.003643499920144677,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.07327796775769418,
      "eval_loss": 11.5,
      "eval_runtime": 21.7893,
      "eval_samples_per_second": 158.243,
      "eval_steps_per_second": 79.122,
      "step": 150
    },
    {
      "epoch": 0.07376648754274548,
      "grad_norm": 0.0026295215357095003,
      "learning_rate": 1.9136088935510362e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.07425500732779677,
      "grad_norm": 0.0019322294974699616,
      "learning_rate": 1.8414449687337464e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.07474352711284807,
      "grad_norm": 0.0024281959049403667,
      "learning_rate": 1.7703596875660645e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.07523204689789936,
      "grad_norm": 0.00209889211691916,
      "learning_rate": 1.700377325606388e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.07572056668295066,
      "grad_norm": 0.0027790747117251158,
      "learning_rate": 1.631521781767214e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.07620908646800195,
      "grad_norm": 0.0029743951745331287,
      "learning_rate": 1.5638165701536868e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.07669760625305325,
      "grad_norm": 0.003012306522578001,
      "learning_rate": 1.4972848120335453e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.07718612603810454,
      "grad_norm": 0.0030355937778949738,
      "learning_rate": 1.4319492279412388e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.07767464582315584,
      "grad_norm": 0.002729633590206504,
      "learning_rate": 1.3678321299188801e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.07816316560820713,
      "grad_norm": 0.003061029827222228,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.07865168539325842,
      "grad_norm": 0.0034317467361688614,
      "learning_rate": 1.2433405522156332e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.07914020517830972,
      "grad_norm": 0.0037723646964877844,
      "learning_rate": 1.183008586294485e-05,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.07962872496336101,
      "grad_norm": 0.003198886290192604,
      "learning_rate": 1.1239801194443506e-05,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.08011724474841231,
      "grad_norm": 0.0031450283713638783,
      "learning_rate": 1.066275309832584e-05,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.0806057645334636,
      "grad_norm": 0.003614857094362378,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.0810942843185149,
      "grad_norm": 0.0034642990212887526,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.08158280410356619,
      "grad_norm": 0.003436095081269741,
      "learning_rate": 9.012975854638949e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.08207132388861749,
      "grad_norm": 0.0033289180137217045,
      "learning_rate": 8.490798459222476e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.08255984367366878,
      "grad_norm": 0.0033829372841864824,
      "learning_rate": 7.982796418105371e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.08304836345872008,
      "grad_norm": 0.003401255002245307,
      "learning_rate": 7.489143213519301e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.08353688324377137,
      "grad_norm": 0.0036590571980923414,
      "learning_rate": 7.010007427581378e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.08402540302882266,
      "grad_norm": 0.003637349233031273,
      "learning_rate": 6.5455526847235825e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.08451392281387396,
      "grad_norm": 0.003337201429530978,
      "learning_rate": 6.0959375958151045e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.08500244259892525,
      "grad_norm": 0.0034019306767731905,
      "learning_rate": 5.6613157039969055e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.08549096238397655,
      "grad_norm": 0.0034504553768783808,
      "learning_rate": 5.241835432246889e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.08597948216902784,
      "grad_norm": 0.003214376512914896,
      "learning_rate": 4.837640032693558e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.08646800195407914,
      "grad_norm": 0.0036590604577213526,
      "learning_rate": 4.448867537695578e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.0033399956300854683,
      "learning_rate": 4.075650712703849e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.08744504152418173,
      "grad_norm": 0.0034210023004561663,
      "learning_rate": 3.71811701092219e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.08793356130923302,
      "grad_norm": 0.003220006823539734,
      "learning_rate": 3.376388529782215e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.08842208109428432,
      "grad_norm": 0.003696272848173976,
      "learning_rate": 3.0505819692471792e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.08891060087933561,
      "grad_norm": 0.003575393231585622,
      "learning_rate": 2.7408085919590264e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.0893991206643869,
      "grad_norm": 0.003938958048820496,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.0898876404494382,
      "grad_norm": 0.0039198389276862144,
      "learning_rate": 2.1697790249779636e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.0903761602344895,
      "grad_norm": 0.0035615130327641964,
      "learning_rate": 1.908717841359048e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.09086468001954079,
      "grad_norm": 0.0030337281059473753,
      "learning_rate": 1.6640797865406288e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.09135319980459208,
      "grad_norm": 0.003380219452083111,
      "learning_rate": 1.4359484041943038e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.09184171958964338,
      "grad_norm": 0.0038383265491575003,
      "learning_rate": 1.2244016009781701e-06,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.09233023937469467,
      "grad_norm": 0.003710967255756259,
      "learning_rate": 1.0295116199317057e-06,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.09281875915974597,
      "grad_norm": 0.003858968149870634,
      "learning_rate": 8.513450158049108e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.09330727894479726,
      "grad_norm": 0.00442510237917304,
      "learning_rate": 6.899626323298713e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.09379579872984856,
      "grad_norm": 0.0036304136738181114,
      "learning_rate": 5.454195814427021e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.09428431851489985,
      "grad_norm": 0.003316792892292142,
      "learning_rate": 4.177652244628627e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.09477283829995115,
      "grad_norm": 0.00361361145041883,
      "learning_rate": 3.0704315523631953e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.09526135808500244,
      "grad_norm": 0.004398842807859182,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.09574987787005373,
      "grad_norm": 0.004400990903377533,
      "learning_rate": 1.3654133071059893e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.09623839765510503,
      "grad_norm": 0.004007602110505104,
      "learning_rate": 7.681980162830282e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.09672691744015632,
      "grad_norm": 0.004391137044876814,
      "learning_rate": 3.4146992848854695e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.09721543722520762,
      "grad_norm": 0.004615367855876684,
      "learning_rate": 8.537477097364522e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.09770395701025891,
      "grad_norm": 0.003925880882889032,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.09770395701025891,
      "eval_loss": 11.5,
      "eval_runtime": 21.7902,
      "eval_samples_per_second": 158.236,
      "eval_steps_per_second": 79.118,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 32721235869696.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}