{
  "best_metric": 0.584774374961853,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.1970928800197093,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009854644000985464,
      "grad_norm": 0.4313327372074127,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0899,
      "step": 1
    },
    {
      "epoch": 0.0009854644000985464,
      "eval_loss": 0.9981184601783752,
      "eval_runtime": 158.8136,
      "eval_samples_per_second": 10.761,
      "eval_steps_per_second": 5.384,
      "step": 1
    },
    {
      "epoch": 0.001970928800197093,
      "grad_norm": 0.5051336884498596,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.3115,
      "step": 2
    },
    {
      "epoch": 0.0029563932002956393,
      "grad_norm": 0.40696489810943604,
      "learning_rate": 1e-05,
      "loss": 0.3648,
      "step": 3
    },
    {
      "epoch": 0.003941857600394186,
      "grad_norm": 0.5555673241615295,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.4126,
      "step": 4
    },
    {
      "epoch": 0.004927322000492732,
      "grad_norm": 0.6959850788116455,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5118,
      "step": 5
    },
    {
      "epoch": 0.005912786400591279,
      "grad_norm": 0.6902092695236206,
      "learning_rate": 2e-05,
      "loss": 0.6241,
      "step": 6
    },
    {
      "epoch": 0.006898250800689825,
      "grad_norm": 0.5990986824035645,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.7635,
      "step": 7
    },
    {
      "epoch": 0.007883715200788372,
      "grad_norm": 0.46151483058929443,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.7826,
      "step": 8
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": 0.40509724617004395,
      "learning_rate": 3e-05,
      "loss": 0.8468,
      "step": 9
    },
    {
      "epoch": 0.009854644000985464,
      "grad_norm": 0.4107632040977478,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7862,
      "step": 10
    },
    {
      "epoch": 0.01084010840108401,
      "grad_norm": 0.4689662754535675,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.7878,
      "step": 11
    },
    {
      "epoch": 0.011825572801182557,
      "grad_norm": 0.4455258250236511,
      "learning_rate": 4e-05,
      "loss": 0.8286,
      "step": 12
    },
    {
      "epoch": 0.012811037201281104,
      "grad_norm": 0.4460776746273041,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.6505,
      "step": 13
    },
    {
      "epoch": 0.01379650160137965,
      "grad_norm": 0.47701597213745117,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.8125,
      "step": 14
    },
    {
      "epoch": 0.014781966001478197,
      "grad_norm": 0.43874800205230713,
      "learning_rate": 5e-05,
      "loss": 0.6508,
      "step": 15
    },
    {
      "epoch": 0.015767430401576743,
      "grad_norm": 0.43464934825897217,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.7736,
      "step": 16
    },
    {
      "epoch": 0.01675289480167529,
      "grad_norm": 0.4389445185661316,
      "learning_rate": 5.666666666666667e-05,
      "loss": 0.7805,
      "step": 17
    },
    {
      "epoch": 0.017738359201773836,
      "grad_norm": 0.33348941802978516,
      "learning_rate": 6e-05,
      "loss": 0.6069,
      "step": 18
    },
    {
      "epoch": 0.018723823601872382,
      "grad_norm": 0.3531840443611145,
      "learning_rate": 6.333333333333333e-05,
      "loss": 0.6574,
      "step": 19
    },
    {
      "epoch": 0.01970928800197093,
      "grad_norm": 0.30243533849716187,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.6736,
      "step": 20
    },
    {
      "epoch": 0.020694752402069475,
      "grad_norm": 0.32596221566200256,
      "learning_rate": 7e-05,
      "loss": 0.6822,
      "step": 21
    },
    {
      "epoch": 0.02168021680216802,
      "grad_norm": 0.3076384365558624,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.7694,
      "step": 22
    },
    {
      "epoch": 0.022665681202266568,
      "grad_norm": 0.30813416838645935,
      "learning_rate": 7.666666666666667e-05,
      "loss": 0.6511,
      "step": 23
    },
    {
      "epoch": 0.023651145602365115,
      "grad_norm": 0.3227630853652954,
      "learning_rate": 8e-05,
      "loss": 0.6856,
      "step": 24
    },
    {
      "epoch": 0.02463661000246366,
      "grad_norm": 0.3547810912132263,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.6536,
      "step": 25
    },
    {
      "epoch": 0.025622074402562207,
      "grad_norm": 0.3056383430957794,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.7591,
      "step": 26
    },
    {
      "epoch": 0.026607538802660754,
      "grad_norm": 0.33836042881011963,
      "learning_rate": 9e-05,
      "loss": 0.8528,
      "step": 27
    },
    {
      "epoch": 0.0275930032027593,
      "grad_norm": 0.3435473144054413,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.7285,
      "step": 28
    },
    {
      "epoch": 0.028578467602857847,
      "grad_norm": 0.3219856917858124,
      "learning_rate": 9.666666666666667e-05,
      "loss": 0.7288,
      "step": 29
    },
    {
      "epoch": 0.029563932002956393,
      "grad_norm": 0.3125074505805969,
      "learning_rate": 0.0001,
      "loss": 0.7225,
      "step": 30
    },
    {
      "epoch": 0.03054939640305494,
      "grad_norm": 0.31725504994392395,
      "learning_rate": 9.999146252290264e-05,
      "loss": 0.7351,
      "step": 31
    },
    {
      "epoch": 0.031534860803153486,
      "grad_norm": 0.3184851109981537,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.7631,
      "step": 32
    },
    {
      "epoch": 0.032520325203252036,
      "grad_norm": 0.36127910017967224,
      "learning_rate": 9.99231801983717e-05,
      "loss": 0.7501,
      "step": 33
    },
    {
      "epoch": 0.03350578960335058,
      "grad_norm": 0.32324203848838806,
      "learning_rate": 9.986345866928941e-05,
      "loss": 0.7823,
      "step": 34
    },
    {
      "epoch": 0.03449125400344913,
      "grad_norm": 0.3167076110839844,
      "learning_rate": 9.978670881475172e-05,
      "loss": 0.6496,
      "step": 35
    },
    {
      "epoch": 0.03547671840354767,
      "grad_norm": 0.3640748858451843,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.6557,
      "step": 36
    },
    {
      "epoch": 0.03646218280364622,
      "grad_norm": 0.40133535861968994,
      "learning_rate": 9.958223477553714e-05,
      "loss": 0.7987,
      "step": 37
    },
    {
      "epoch": 0.037447647203744765,
      "grad_norm": 0.40022367238998413,
      "learning_rate": 9.94545804185573e-05,
      "loss": 0.7052,
      "step": 38
    },
    {
      "epoch": 0.038433111603843315,
      "grad_norm": 0.4175143241882324,
      "learning_rate": 9.931003736767013e-05,
      "loss": 0.7733,
      "step": 39
    },
    {
      "epoch": 0.03941857600394186,
      "grad_norm": 0.5691938996315002,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.6385,
      "step": 40
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 0.36552998423576355,
      "learning_rate": 9.89704883800683e-05,
      "loss": 0.5661,
      "step": 41
    },
    {
      "epoch": 0.04138950480413895,
      "grad_norm": 0.44288337230682373,
      "learning_rate": 9.877559839902184e-05,
      "loss": 0.7711,
      "step": 42
    },
    {
      "epoch": 0.0423749692042375,
      "grad_norm": 0.42461535334587097,
      "learning_rate": 9.85640515958057e-05,
      "loss": 0.7106,
      "step": 43
    },
    {
      "epoch": 0.04336043360433604,
      "grad_norm": 0.46416065096855164,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.7392,
      "step": 44
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": 0.46228498220443726,
      "learning_rate": 9.809128215864097e-05,
      "loss": 0.6193,
      "step": 45
    },
    {
      "epoch": 0.045331362404533136,
      "grad_norm": 0.5916977524757385,
      "learning_rate": 9.783022097502204e-05,
      "loss": 0.9369,
      "step": 46
    },
    {
      "epoch": 0.046316826804631686,
      "grad_norm": 0.509521484375,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8942,
      "step": 47
    },
    {
      "epoch": 0.04730229120473023,
      "grad_norm": 0.5575716495513916,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.7795,
      "step": 48
    },
    {
      "epoch": 0.04828775560482878,
      "grad_norm": 0.674028754234314,
      "learning_rate": 9.694941803075283e-05,
      "loss": 0.9203,
      "step": 49
    },
    {
      "epoch": 0.04927322000492732,
      "grad_norm": 0.8474329113960266,
      "learning_rate": 9.662361147021779e-05,
      "loss": 0.9088,
      "step": 50
    },
    {
      "epoch": 0.04927322000492732,
      "eval_loss": 0.6253278255462646,
      "eval_runtime": 160.106,
      "eval_samples_per_second": 10.674,
      "eval_steps_per_second": 5.34,
      "step": 50
    },
    {
      "epoch": 0.05025868440502587,
      "grad_norm": 0.09365927428007126,
      "learning_rate": 9.628188298907782e-05,
      "loss": 0.0552,
      "step": 51
    },
    {
      "epoch": 0.051244148805124415,
      "grad_norm": 0.13093718886375427,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.1879,
      "step": 52
    },
    {
      "epoch": 0.052229613205222965,
      "grad_norm": 0.17437294125556946,
      "learning_rate": 9.555113246230442e-05,
      "loss": 0.23,
      "step": 53
    },
    {
      "epoch": 0.05321507760532151,
      "grad_norm": 0.2906794250011444,
      "learning_rate": 9.516235996730645e-05,
      "loss": 0.3665,
      "step": 54
    },
    {
      "epoch": 0.05420054200542006,
      "grad_norm": 0.2222241759300232,
      "learning_rate": 9.475816456775313e-05,
      "loss": 0.4059,
      "step": 55
    },
    {
      "epoch": 0.0551860064055186,
      "grad_norm": 0.24162358045578003,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.5642,
      "step": 56
    },
    {
      "epoch": 0.05617147080561715,
      "grad_norm": 0.21459117531776428,
      "learning_rate": 9.39040624041849e-05,
      "loss": 0.6121,
      "step": 57
    },
    {
      "epoch": 0.057156935205715693,
      "grad_norm": 0.2023555487394333,
      "learning_rate": 9.345444731527642e-05,
      "loss": 0.5059,
      "step": 58
    },
    {
      "epoch": 0.05814239960581424,
      "grad_norm": 0.2224394828081131,
      "learning_rate": 9.298999257241863e-05,
      "loss": 0.6517,
      "step": 59
    },
    {
      "epoch": 0.059127864005912786,
      "grad_norm": 0.24458082020282745,
      "learning_rate": 9.251085678648072e-05,
      "loss": 0.7442,
      "step": 60
    },
    {
      "epoch": 0.060113328406011336,
      "grad_norm": 0.22274242341518402,
      "learning_rate": 9.201720358189464e-05,
      "loss": 0.6335,
      "step": 61
    },
    {
      "epoch": 0.06109879280610988,
      "grad_norm": 0.2185131013393402,
      "learning_rate": 9.150920154077754e-05,
      "loss": 0.5323,
      "step": 62
    },
    {
      "epoch": 0.06208425720620843,
      "grad_norm": 0.21939384937286377,
      "learning_rate": 9.098702414536107e-05,
      "loss": 0.6066,
      "step": 63
    },
    {
      "epoch": 0.06306972160630697,
      "grad_norm": 0.20755380392074585,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5819,
      "step": 64
    },
    {
      "epoch": 0.06405518600640552,
      "grad_norm": 0.2545813024044037,
      "learning_rate": 8.9900861364012e-05,
      "loss": 0.7208,
      "step": 65
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 0.25121399760246277,
      "learning_rate": 8.933724690167417e-05,
      "loss": 0.8203,
      "step": 66
    },
    {
      "epoch": 0.06602611480660261,
      "grad_norm": 0.23934347927570343,
      "learning_rate": 8.876019880555649e-05,
      "loss": 0.6853,
      "step": 67
    },
    {
      "epoch": 0.06701157920670116,
      "grad_norm": 0.2448682188987732,
      "learning_rate": 8.816991413705516e-05,
      "loss": 0.8493,
      "step": 68
    },
    {
      "epoch": 0.0679970436067997,
      "grad_norm": 0.21752771735191345,
      "learning_rate": 8.756659447784368e-05,
      "loss": 0.4707,
      "step": 69
    },
    {
      "epoch": 0.06898250800689826,
      "grad_norm": 0.2293497771024704,
      "learning_rate": 8.695044586103296e-05,
      "loss": 0.6304,
      "step": 70
    },
    {
      "epoch": 0.0699679724069968,
      "grad_norm": 0.24045786261558533,
      "learning_rate": 8.632167870081121e-05,
      "loss": 0.6314,
      "step": 71
    },
    {
      "epoch": 0.07095343680709534,
      "grad_norm": 0.26281052827835083,
      "learning_rate": 8.568050772058762e-05,
      "loss": 0.619,
      "step": 72
    },
    {
      "epoch": 0.07193890120719389,
      "grad_norm": 0.28175660967826843,
      "learning_rate": 8.502715187966455e-05,
      "loss": 0.7979,
      "step": 73
    },
    {
      "epoch": 0.07292436560729244,
      "grad_norm": 0.2699892520904541,
      "learning_rate": 8.436183429846313e-05,
      "loss": 0.7732,
      "step": 74
    },
    {
      "epoch": 0.07390983000739099,
      "grad_norm": 0.2922893166542053,
      "learning_rate": 8.368478218232787e-05,
      "loss": 0.8827,
      "step": 75
    },
    {
      "epoch": 0.07489529440748953,
      "grad_norm": 0.27122068405151367,
      "learning_rate": 8.299622674393614e-05,
      "loss": 0.6182,
      "step": 76
    },
    {
      "epoch": 0.07588075880758807,
      "grad_norm": 0.28131553530693054,
      "learning_rate": 8.229640312433937e-05,
      "loss": 0.6974,
      "step": 77
    },
    {
      "epoch": 0.07686622320768663,
      "grad_norm": 0.26899459958076477,
      "learning_rate": 8.158555031266254e-05,
      "loss": 0.6486,
      "step": 78
    },
    {
      "epoch": 0.07785168760778517,
      "grad_norm": 0.31664565205574036,
      "learning_rate": 8.086391106448965e-05,
      "loss": 0.7727,
      "step": 79
    },
    {
      "epoch": 0.07883715200788372,
      "grad_norm": 0.28200066089630127,
      "learning_rate": 8.013173181896283e-05,
      "loss": 0.643,
      "step": 80
    },
    {
      "epoch": 0.07982261640798226,
      "grad_norm": 0.3218248188495636,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7016,
      "step": 81
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 0.32966381311416626,
      "learning_rate": 7.863675700402526e-05,
      "loss": 0.7472,
      "step": 82
    },
    {
      "epoch": 0.08179354520817936,
      "grad_norm": 0.31329721212387085,
      "learning_rate": 7.787447196714427e-05,
      "loss": 0.7025,
      "step": 83
    },
    {
      "epoch": 0.0827790096082779,
      "grad_norm": 0.29452916979789734,
      "learning_rate": 7.710266782362247e-05,
      "loss": 0.6234,
      "step": 84
    },
    {
      "epoch": 0.08376447400837644,
      "grad_norm": 0.34324830770492554,
      "learning_rate": 7.63216081438678e-05,
      "loss": 0.6944,
      "step": 85
    },
    {
      "epoch": 0.084749938408475,
      "grad_norm": 0.33645856380462646,
      "learning_rate": 7.553155965904535e-05,
      "loss": 0.6598,
      "step": 86
    },
    {
      "epoch": 0.08573540280857354,
      "grad_norm": 0.33191972970962524,
      "learning_rate": 7.473279216998895e-05,
      "loss": 0.6206,
      "step": 87
    },
    {
      "epoch": 0.08672086720867209,
      "grad_norm": 0.4066058099269867,
      "learning_rate": 7.392557845506432e-05,
      "loss": 0.7335,
      "step": 88
    },
    {
      "epoch": 0.08770633160877063,
      "grad_norm": 0.37192967534065247,
      "learning_rate": 7.311019417701566e-05,
      "loss": 0.6201,
      "step": 89
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": 0.40204325318336487,
      "learning_rate": 7.228691778882693e-05,
      "loss": 0.691,
      "step": 90
    },
    {
      "epoch": 0.08967726040896773,
      "grad_norm": 0.3774620592594147,
      "learning_rate": 7.145603043863045e-05,
      "loss": 0.6234,
      "step": 91
    },
    {
      "epoch": 0.09066272480906627,
      "grad_norm": 0.38905617594718933,
      "learning_rate": 7.061781587369519e-05,
      "loss": 0.5785,
      "step": 92
    },
    {
      "epoch": 0.09164818920916482,
      "grad_norm": 0.40719079971313477,
      "learning_rate": 6.977256034352712e-05,
      "loss": 0.7717,
      "step": 93
    },
    {
      "epoch": 0.09263365360926337,
      "grad_norm": 0.42338162660598755,
      "learning_rate": 6.892055250211552e-05,
      "loss": 0.7243,
      "step": 94
    },
    {
      "epoch": 0.09361911800936192,
      "grad_norm": 0.4960746169090271,
      "learning_rate": 6.806208330935766e-05,
      "loss": 0.694,
      "step": 95
    },
    {
      "epoch": 0.09460458240946046,
      "grad_norm": 0.45286256074905396,
      "learning_rate": 6.719744593169641e-05,
      "loss": 0.7173,
      "step": 96
    },
    {
      "epoch": 0.095590046809559,
      "grad_norm": 0.47811850905418396,
      "learning_rate": 6.632693564200416e-05,
      "loss": 0.7395,
      "step": 97
    },
    {
      "epoch": 0.09657551120965756,
      "grad_norm": 0.5401033759117126,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7726,
      "step": 98
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.6063845157623291,
      "learning_rate": 6.456948734446624e-05,
      "loss": 0.8667,
      "step": 99
    },
    {
      "epoch": 0.09854644000985464,
      "grad_norm": 0.7505123615264893,
      "learning_rate": 6.368314950360415e-05,
      "loss": 0.6364,
      "step": 100
    },
    {
      "epoch": 0.09854644000985464,
      "eval_loss": 0.6039547920227051,
      "eval_runtime": 159.9711,
      "eval_samples_per_second": 10.683,
      "eval_steps_per_second": 5.345,
      "step": 100
    },
    {
      "epoch": 0.09953190440995319,
      "grad_norm": 0.06492675840854645,
      "learning_rate": 6.279213887972179e-05,
      "loss": 0.0378,
      "step": 101
    },
    {
      "epoch": 0.10051736881005174,
      "grad_norm": 0.10757127404212952,
      "learning_rate": 6.189675975213094e-05,
      "loss": 0.1717,
      "step": 102
    },
    {
      "epoch": 0.10150283321015029,
      "grad_norm": 0.139942467212677,
      "learning_rate": 6.099731789198344e-05,
      "loss": 0.2134,
      "step": 103
    },
    {
      "epoch": 0.10248829761024883,
      "grad_norm": 0.17105042934417725,
      "learning_rate": 6.009412045785051e-05,
      "loss": 0.242,
      "step": 104
    },
    {
      "epoch": 0.10347376201034737,
      "grad_norm": 0.1677185744047165,
      "learning_rate": 5.918747589082853e-05,
      "loss": 0.2773,
      "step": 105
    },
    {
      "epoch": 0.10445922641044593,
      "grad_norm": 0.19385424256324768,
      "learning_rate": 5.82776938092065e-05,
      "loss": 0.4616,
      "step": 106
    },
    {
      "epoch": 0.10544469081054447,
      "grad_norm": 0.19936293363571167,
      "learning_rate": 5.736508490273188e-05,
      "loss": 0.5253,
      "step": 107
    },
    {
      "epoch": 0.10643015521064302,
      "grad_norm": 0.225832998752594,
      "learning_rate": 5.644996082651017e-05,
      "loss": 0.6073,
      "step": 108
    },
    {
      "epoch": 0.10741561961074156,
      "grad_norm": 0.20826251804828644,
      "learning_rate": 5.553263409457504e-05,
      "loss": 0.5133,
      "step": 109
    },
    {
      "epoch": 0.10840108401084012,
      "grad_norm": 0.19744732975959778,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 0.5992,
      "step": 110
    },
    {
      "epoch": 0.10938654841093866,
      "grad_norm": 0.20350094139575958,
      "learning_rate": 5.3692626373743706e-05,
      "loss": 0.5886,
      "step": 111
    },
    {
      "epoch": 0.1103720128110372,
      "grad_norm": 0.2253555953502655,
      "learning_rate": 5.27705737457985e-05,
      "loss": 0.7352,
      "step": 112
    },
    {
      "epoch": 0.11135747721113574,
      "grad_norm": 0.1978590339422226,
      "learning_rate": 5.184757496945726e-05,
      "loss": 0.6002,
      "step": 113
    },
    {
      "epoch": 0.1123429416112343,
      "grad_norm": 0.23348231613636017,
      "learning_rate": 5.092394524795649e-05,
      "loss": 0.5746,
      "step": 114
    },
    {
      "epoch": 0.11332840601133284,
      "grad_norm": 0.223561093211174,
      "learning_rate": 5e-05,
      "loss": 0.7063,
      "step": 115
    },
    {
      "epoch": 0.11431387041143139,
      "grad_norm": 0.22021301090717316,
      "learning_rate": 4.907605475204352e-05,
      "loss": 0.5453,
      "step": 116
    },
    {
      "epoch": 0.11529933481152993,
      "grad_norm": 0.22918701171875,
      "learning_rate": 4.8152425030542766e-05,
      "loss": 0.6408,
      "step": 117
    },
    {
      "epoch": 0.11628479921162849,
      "grad_norm": 0.221017986536026,
      "learning_rate": 4.72294262542015e-05,
      "loss": 0.6825,
      "step": 118
    },
    {
      "epoch": 0.11727026361172703,
      "grad_norm": 0.24463246762752533,
      "learning_rate": 4.6307373626256306e-05,
      "loss": 0.674,
      "step": 119
    },
    {
      "epoch": 0.11825572801182557,
      "grad_norm": 0.22127676010131836,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 0.5877,
      "step": 120
    },
    {
      "epoch": 0.11924119241192412,
      "grad_norm": 0.25243082642555237,
      "learning_rate": 4.446736590542497e-05,
      "loss": 0.7659,
      "step": 121
    },
    {
      "epoch": 0.12022665681202267,
      "grad_norm": 0.25524279475212097,
      "learning_rate": 4.3550039173489845e-05,
      "loss": 0.7332,
      "step": 122
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.2742602527141571,
      "learning_rate": 4.2634915097268115e-05,
      "loss": 0.8811,
      "step": 123
    },
    {
      "epoch": 0.12219758561221976,
      "grad_norm": 0.2482510656118393,
      "learning_rate": 4.1722306190793495e-05,
      "loss": 0.7613,
      "step": 124
    },
    {
      "epoch": 0.1231830500123183,
      "grad_norm": 0.2792511284351349,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 0.7514,
      "step": 125
    },
    {
      "epoch": 0.12416851441241686,
      "grad_norm": 0.28039655089378357,
      "learning_rate": 3.99058795421495e-05,
      "loss": 0.6821,
      "step": 126
    },
    {
      "epoch": 0.1251539788125154,
      "grad_norm": 0.3473927080631256,
      "learning_rate": 3.9002682108016585e-05,
      "loss": 0.6593,
      "step": 127
    },
    {
      "epoch": 0.12613944321261394,
      "grad_norm": 0.2565251290798187,
      "learning_rate": 3.8103240247869075e-05,
      "loss": 0.5399,
      "step": 128
    },
    {
      "epoch": 0.1271249076127125,
      "grad_norm": 0.28116095066070557,
      "learning_rate": 3.720786112027822e-05,
      "loss": 0.6255,
      "step": 129
    },
    {
      "epoch": 0.12811037201281103,
      "grad_norm": 0.28025346994400024,
      "learning_rate": 3.631685049639586e-05,
      "loss": 0.7028,
      "step": 130
    },
    {
      "epoch": 0.1290958364129096,
      "grad_norm": 0.2895910441875458,
      "learning_rate": 3.543051265553377e-05,
      "loss": 0.7361,
      "step": 131
    },
    {
      "epoch": 0.13008130081300814,
      "grad_norm": 0.2944524884223938,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7275,
      "step": 132
    },
    {
      "epoch": 0.13106676521310667,
      "grad_norm": 0.334114134311676,
      "learning_rate": 3.367306435799584e-05,
      "loss": 0.8179,
      "step": 133
    },
    {
      "epoch": 0.13205222961320523,
      "grad_norm": 0.3113299012184143,
      "learning_rate": 3.2802554068303596e-05,
      "loss": 0.7505,
      "step": 134
    },
    {
      "epoch": 0.13303769401330376,
      "grad_norm": 0.3196057677268982,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 0.7061,
      "step": 135
    },
    {
      "epoch": 0.13402315841340232,
      "grad_norm": 0.3126354217529297,
      "learning_rate": 3.107944749788449e-05,
      "loss": 0.7001,
      "step": 136
    },
    {
      "epoch": 0.13500862281350087,
      "grad_norm": 0.31723636388778687,
      "learning_rate": 3.0227439656472877e-05,
      "loss": 0.5961,
      "step": 137
    },
    {
      "epoch": 0.1359940872135994,
      "grad_norm": 0.3157641291618347,
      "learning_rate": 2.9382184126304834e-05,
      "loss": 0.5105,
      "step": 138
    },
    {
      "epoch": 0.13697955161369796,
      "grad_norm": 0.337483286857605,
      "learning_rate": 2.8543969561369556e-05,
      "loss": 0.6706,
      "step": 139
    },
    {
      "epoch": 0.13796501601379652,
      "grad_norm": 0.35467472672462463,
      "learning_rate": 2.771308221117309e-05,
      "loss": 0.6632,
      "step": 140
    },
    {
      "epoch": 0.13895048041389504,
      "grad_norm": 0.3754487633705139,
      "learning_rate": 2.688980582298435e-05,
      "loss": 0.6372,
      "step": 141
    },
    {
      "epoch": 0.1399359448139936,
      "grad_norm": 0.3946709930896759,
      "learning_rate": 2.607442154493568e-05,
      "loss": 0.7413,
      "step": 142
    },
    {
      "epoch": 0.14092140921409213,
      "grad_norm": 0.37810003757476807,
      "learning_rate": 2.5267207830011068e-05,
      "loss": 0.6634,
      "step": 143
    },
    {
      "epoch": 0.1419068736141907,
      "grad_norm": 0.3932291567325592,
      "learning_rate": 2.446844034095466e-05,
      "loss": 0.6756,
      "step": 144
    },
    {
      "epoch": 0.14289233801428924,
      "grad_norm": 0.42648932337760925,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 0.7081,
      "step": 145
    },
    {
      "epoch": 0.14387780241438777,
      "grad_norm": 0.46039843559265137,
      "learning_rate": 2.2897332176377528e-05,
      "loss": 0.8046,
      "step": 146
    },
    {
      "epoch": 0.14486326681448633,
      "grad_norm": 0.4435557425022125,
      "learning_rate": 2.2125528032855724e-05,
      "loss": 0.6347,
      "step": 147
    },
    {
      "epoch": 0.1458487312145849,
      "grad_norm": 0.509733259677887,
      "learning_rate": 2.136324299597474e-05,
      "loss": 0.8318,
      "step": 148
    },
    {
      "epoch": 0.14683419561468342,
      "grad_norm": 0.5783795714378357,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.662,
      "step": 149
    },
    {
      "epoch": 0.14781966001478197,
      "grad_norm": 0.8224442005157471,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 0.6612,
      "step": 150
    },
    {
      "epoch": 0.14781966001478197,
      "eval_loss": 0.5897608995437622,
      "eval_runtime": 160.4128,
      "eval_samples_per_second": 10.654,
      "eval_steps_per_second": 5.33,
      "step": 150
    },
    {
      "epoch": 0.1488051244148805,
      "grad_norm": 0.04582216218113899,
      "learning_rate": 1.9136088935510362e-05,
      "loss": 0.0314,
      "step": 151
    },
    {
      "epoch": 0.14979058881497906,
      "grad_norm": 0.09543165564537048,
      "learning_rate": 1.8414449687337464e-05,
      "loss": 0.1812,
      "step": 152
    },
    {
      "epoch": 0.15077605321507762,
      "grad_norm": 0.10564053803682327,
      "learning_rate": 1.7703596875660645e-05,
      "loss": 0.259,
      "step": 153
    },
    {
      "epoch": 0.15176151761517614,
      "grad_norm": 0.1349058598279953,
      "learning_rate": 1.700377325606388e-05,
      "loss": 0.3295,
      "step": 154
    },
    {
      "epoch": 0.1527469820152747,
      "grad_norm": 0.16049978137016296,
      "learning_rate": 1.631521781767214e-05,
      "loss": 0.4605,
      "step": 155
    },
    {
      "epoch": 0.15373244641537326,
      "grad_norm": 0.19529177248477936,
      "learning_rate": 1.5638165701536868e-05,
      "loss": 0.6925,
      "step": 156
    },
    {
      "epoch": 0.1547179108154718,
      "grad_norm": 0.14760489761829376,
      "learning_rate": 1.4972848120335453e-05,
      "loss": 0.4273,
      "step": 157
    },
    {
      "epoch": 0.15570337521557034,
      "grad_norm": 0.1731565296649933,
      "learning_rate": 1.4319492279412388e-05,
      "loss": 0.4982,
      "step": 158
    },
    {
      "epoch": 0.15668883961566887,
      "grad_norm": 0.19718369841575623,
      "learning_rate": 1.3678321299188801e-05,
      "loss": 0.5252,
      "step": 159
    },
    {
      "epoch": 0.15767430401576743,
      "grad_norm": 0.19219151139259338,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 0.6744,
      "step": 160
    },
    {
      "epoch": 0.158659768415866,
      "grad_norm": 0.19782665371894836,
      "learning_rate": 1.2433405522156332e-05,
      "loss": 0.5857,
      "step": 161
    },
    {
      "epoch": 0.15964523281596452,
      "grad_norm": 0.19759586453437805,
      "learning_rate": 1.183008586294485e-05,
      "loss": 0.6169,
      "step": 162
    },
    {
      "epoch": 0.16063069721606307,
      "grad_norm": 0.2008185088634491,
      "learning_rate": 1.1239801194443506e-05,
      "loss": 0.5558,
      "step": 163
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.20355170965194702,
      "learning_rate": 1.066275309832584e-05,
      "loss": 0.6305,
      "step": 164
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 0.2057691514492035,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 0.629,
      "step": 165
    },
    {
      "epoch": 0.16358709041635872,
      "grad_norm": 0.21220219135284424,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5687,
      "step": 166
    },
    {
      "epoch": 0.16457255481645724,
      "grad_norm": 0.22451376914978027,
      "learning_rate": 9.012975854638949e-06,
      "loss": 0.7258,
      "step": 167
    },
    {
      "epoch": 0.1655580192165558,
      "grad_norm": 0.24449403584003448,
      "learning_rate": 8.490798459222476e-06,
      "loss": 0.6929,
      "step": 168
    },
    {
      "epoch": 0.16654348361665436,
      "grad_norm": 0.2417096346616745,
      "learning_rate": 7.982796418105371e-06,
      "loss": 0.7392,
      "step": 169
    },
    {
      "epoch": 0.1675289480167529,
      "grad_norm": 0.27315232157707214,
      "learning_rate": 7.489143213519301e-06,
      "loss": 0.7316,
      "step": 170
    },
    {
      "epoch": 0.16851441241685144,
      "grad_norm": 0.25194498896598816,
      "learning_rate": 7.010007427581378e-06,
      "loss": 0.5979,
      "step": 171
    },
    {
      "epoch": 0.16949987681695,
      "grad_norm": 0.24112963676452637,
      "learning_rate": 6.5455526847235825e-06,
      "loss": 0.69,
      "step": 172
    },
    {
      "epoch": 0.17048534121704853,
      "grad_norm": 0.2511669397354126,
      "learning_rate": 6.0959375958151045e-06,
      "loss": 0.5824,
      "step": 173
    },
    {
      "epoch": 0.1714708056171471,
      "grad_norm": 0.24215401709079742,
      "learning_rate": 5.6613157039969055e-06,
      "loss": 0.6823,
      "step": 174
    },
    {
      "epoch": 0.17245627001724562,
      "grad_norm": 0.28520438075065613,
      "learning_rate": 5.241835432246889e-06,
      "loss": 0.7416,
      "step": 175
    },
    {
      "epoch": 0.17344173441734417,
      "grad_norm": 0.2623746395111084,
      "learning_rate": 4.837640032693558e-06,
      "loss": 0.6514,
      "step": 176
    },
    {
      "epoch": 0.17442719881744273,
      "grad_norm": 0.2783282995223999,
      "learning_rate": 4.448867537695578e-06,
      "loss": 0.7159,
      "step": 177
    },
    {
      "epoch": 0.17541266321754126,
      "grad_norm": 0.27611035108566284,
      "learning_rate": 4.075650712703849e-06,
      "loss": 0.7525,
      "step": 178
    },
    {
      "epoch": 0.17639812761763982,
      "grad_norm": 0.270900696516037,
      "learning_rate": 3.71811701092219e-06,
      "loss": 0.7557,
      "step": 179
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": 0.2633064389228821,
      "learning_rate": 3.376388529782215e-06,
      "loss": 0.5719,
      "step": 180
    },
    {
      "epoch": 0.1783690564178369,
      "grad_norm": 0.2590899169445038,
      "learning_rate": 3.0505819692471792e-06,
      "loss": 0.5344,
      "step": 181
    },
    {
      "epoch": 0.17935452081793546,
      "grad_norm": 0.28156155347824097,
      "learning_rate": 2.7408085919590264e-06,
      "loss": 0.6333,
      "step": 182
    },
    {
      "epoch": 0.180339985218034,
      "grad_norm": 0.2902732491493225,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5511,
      "step": 183
    },
    {
      "epoch": 0.18132544961813254,
      "grad_norm": 0.3187778890132904,
      "learning_rate": 2.1697790249779636e-06,
      "loss": 0.7326,
      "step": 184
    },
    {
      "epoch": 0.1823109140182311,
      "grad_norm": 0.2755086421966553,
      "learning_rate": 1.908717841359048e-06,
      "loss": 0.4491,
      "step": 185
    },
    {
      "epoch": 0.18329637841832963,
      "grad_norm": 0.33460649847984314,
      "learning_rate": 1.6640797865406288e-06,
      "loss": 0.6483,
      "step": 186
    },
    {
      "epoch": 0.1842818428184282,
      "grad_norm": 0.3185296356678009,
      "learning_rate": 1.4359484041943038e-06,
      "loss": 0.6061,
      "step": 187
    },
    {
      "epoch": 0.18526730721852674,
      "grad_norm": 0.343330055475235,
      "learning_rate": 1.2244016009781701e-06,
      "loss": 0.7053,
      "step": 188
    },
    {
      "epoch": 0.18625277161862527,
      "grad_norm": 0.35610195994377136,
      "learning_rate": 1.0295116199317057e-06,
      "loss": 0.6565,
      "step": 189
    },
    {
      "epoch": 0.18723823601872383,
      "grad_norm": 0.3516658842563629,
      "learning_rate": 8.513450158049108e-07,
      "loss": 0.7232,
      "step": 190
    },
    {
      "epoch": 0.18822370041882236,
      "grad_norm": 0.37256768345832825,
      "learning_rate": 6.899626323298713e-07,
      "loss": 0.5819,
      "step": 191
    },
    {
      "epoch": 0.18920916481892092,
      "grad_norm": 0.4146597385406494,
      "learning_rate": 5.454195814427021e-07,
      "loss": 0.653,
      "step": 192
    },
    {
      "epoch": 0.19019462921901947,
      "grad_norm": 0.3835974335670471,
      "learning_rate": 4.177652244628627e-07,
      "loss": 0.6009,
      "step": 193
    },
    {
      "epoch": 0.191180093619118,
      "grad_norm": 0.5377586483955383,
      "learning_rate": 3.0704315523631953e-07,
      "loss": 0.7371,
      "step": 194
    },
    {
      "epoch": 0.19216555801921656,
      "grad_norm": 0.4629654884338379,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 0.7908,
      "step": 195
    },
    {
      "epoch": 0.19315102241931512,
      "grad_norm": 0.4720406234264374,
      "learning_rate": 1.3654133071059893e-07,
      "loss": 0.7832,
      "step": 196
    },
    {
      "epoch": 0.19413648681941365,
      "grad_norm": 0.5157343745231628,
      "learning_rate": 7.681980162830282e-08,
      "loss": 0.8257,
      "step": 197
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.5014312267303467,
      "learning_rate": 3.4146992848854695e-08,
      "loss": 0.7237,
      "step": 198
    },
    {
      "epoch": 0.19610741561961073,
      "grad_norm": 0.5394123792648315,
      "learning_rate": 8.537477097364522e-09,
      "loss": 0.6931,
      "step": 199
    },
    {
      "epoch": 0.1970928800197093,
      "grad_norm": 0.6996267437934875,
      "learning_rate": 0.0,
      "loss": 0.7056,
      "step": 200
    },
    {
      "epoch": 0.1970928800197093,
      "eval_loss": 0.584774374961853,
      "eval_runtime": 160.1549,
      "eval_samples_per_second": 10.671,
      "eval_steps_per_second": 5.339,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.401698120071905e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}