{
  "best_metric": 0.8421279191970825,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.029961424665742857,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014980712332871428,
      "grad_norm": 0.6298632621765137,
      "learning_rate": 1e-05,
      "loss": 0.8866,
      "step": 1
    },
    {
      "epoch": 0.00014980712332871428,
      "eval_loss": 1.264488935470581,
      "eval_runtime": 565.4748,
      "eval_samples_per_second": 19.882,
      "eval_steps_per_second": 4.971,
      "step": 1
    },
    {
      "epoch": 0.00029961424665742855,
      "grad_norm": 0.46446141600608826,
      "learning_rate": 2e-05,
      "loss": 0.7634,
      "step": 2
    },
    {
      "epoch": 0.00044942136998614283,
      "grad_norm": 0.8355027437210083,
      "learning_rate": 3e-05,
      "loss": 0.9169,
      "step": 3
    },
    {
      "epoch": 0.0005992284933148571,
      "grad_norm": 0.644906222820282,
      "learning_rate": 4e-05,
      "loss": 0.9282,
      "step": 4
    },
    {
      "epoch": 0.0007490356166435714,
      "grad_norm": 0.49212518334388733,
      "learning_rate": 5e-05,
      "loss": 0.9798,
      "step": 5
    },
    {
      "epoch": 0.0008988427399722857,
      "grad_norm": 0.44296741485595703,
      "learning_rate": 6e-05,
      "loss": 1.0082,
      "step": 6
    },
    {
      "epoch": 0.001048649863301,
      "grad_norm": 0.3797648847103119,
      "learning_rate": 7e-05,
      "loss": 0.9093,
      "step": 7
    },
    {
      "epoch": 0.0011984569866297142,
      "grad_norm": 0.3763546049594879,
      "learning_rate": 8e-05,
      "loss": 1.0401,
      "step": 8
    },
    {
      "epoch": 0.0013482641099584285,
      "grad_norm": 0.3808014988899231,
      "learning_rate": 9e-05,
      "loss": 1.0106,
      "step": 9
    },
    {
      "epoch": 0.0014980712332871428,
      "grad_norm": 0.3745298385620117,
      "learning_rate": 0.0001,
      "loss": 0.9575,
      "step": 10
    },
    {
      "epoch": 0.001647878356615857,
      "grad_norm": 0.39324429631233215,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9435,
      "step": 11
    },
    {
      "epoch": 0.0017976854799445713,
      "grad_norm": 0.3526301085948944,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8208,
      "step": 12
    },
    {
      "epoch": 0.0019474926032732856,
      "grad_norm": 0.37045592069625854,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9634,
      "step": 13
    },
    {
      "epoch": 0.002097299726602,
      "grad_norm": 0.33772504329681396,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8449,
      "step": 14
    },
    {
      "epoch": 0.0022471068499307144,
      "grad_norm": 0.43836352229118347,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.6716,
      "step": 15
    },
    {
      "epoch": 0.0023969139732594284,
      "grad_norm": 0.3777485191822052,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8852,
      "step": 16
    },
    {
      "epoch": 0.002546721096588143,
      "grad_norm": 0.36619219183921814,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8873,
      "step": 17
    },
    {
      "epoch": 0.002696528219916857,
      "grad_norm": 0.3267233073711395,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.855,
      "step": 18
    },
    {
      "epoch": 0.0028463353432455715,
      "grad_norm": 0.32704541087150574,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8803,
      "step": 19
    },
    {
      "epoch": 0.0029961424665742855,
      "grad_norm": 0.4222426414489746,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8979,
      "step": 20
    },
    {
      "epoch": 0.003145949589903,
      "grad_norm": 0.33164480328559875,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7718,
      "step": 21
    },
    {
      "epoch": 0.003295756713231714,
      "grad_norm": 0.32442235946655273,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6811,
      "step": 22
    },
    {
      "epoch": 0.0034455638365604286,
      "grad_norm": 0.3956811726093292,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8274,
      "step": 23
    },
    {
      "epoch": 0.0035953709598891426,
      "grad_norm": 0.4070234000682831,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8034,
      "step": 24
    },
    {
      "epoch": 0.003745178083217857,
      "grad_norm": 0.30631351470947266,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7311,
      "step": 25
    },
    {
      "epoch": 0.003894985206546571,
      "grad_norm": 0.34183362126350403,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8869,
      "step": 26
    },
    {
      "epoch": 0.004044792329875285,
      "grad_norm": 0.29005616903305054,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8703,
      "step": 27
    },
    {
      "epoch": 0.004194599453204,
      "grad_norm": 0.359518826007843,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8542,
      "step": 28
    },
    {
      "epoch": 0.004344406576532714,
      "grad_norm": 0.35285744071006775,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7862,
      "step": 29
    },
    {
      "epoch": 0.004494213699861429,
      "grad_norm": 0.32191500067710876,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7777,
      "step": 30
    },
    {
      "epoch": 0.004644020823190142,
      "grad_norm": 0.34467917680740356,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8035,
      "step": 31
    },
    {
      "epoch": 0.004793827946518857,
      "grad_norm": 0.31413033604621887,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8019,
      "step": 32
    },
    {
      "epoch": 0.004943635069847571,
      "grad_norm": 0.33082014322280884,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7154,
      "step": 33
    },
    {
      "epoch": 0.005093442193176286,
      "grad_norm": 0.34413284063339233,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6867,
      "step": 34
    },
    {
      "epoch": 0.0052432493165049995,
      "grad_norm": 0.3844047486782074,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8222,
      "step": 35
    },
    {
      "epoch": 0.005393056439833714,
      "grad_norm": 0.47779640555381775,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8534,
      "step": 36
    },
    {
      "epoch": 0.0055428635631624285,
      "grad_norm": 2.2068326473236084,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8379,
      "step": 37
    },
    {
      "epoch": 0.005692670686491143,
      "grad_norm": 0.41778677701950073,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.9006,
      "step": 38
    },
    {
      "epoch": 0.005842477809819857,
      "grad_norm": 0.4241478145122528,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9492,
      "step": 39
    },
    {
      "epoch": 0.005992284933148571,
      "grad_norm": 0.4319832921028137,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.0443,
      "step": 40
    },
    {
      "epoch": 0.0061420920564772856,
      "grad_norm": 0.36160099506378174,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6914,
      "step": 41
    },
    {
      "epoch": 0.006291899179806,
      "grad_norm": 0.4357793629169464,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.872,
      "step": 42
    },
    {
      "epoch": 0.006441706303134714,
      "grad_norm": 0.4501705467700958,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8288,
      "step": 43
    },
    {
      "epoch": 0.006591513426463428,
      "grad_norm": 0.5566861033439636,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9786,
      "step": 44
    },
    {
      "epoch": 0.006741320549792143,
      "grad_norm": 0.5371454954147339,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9145,
      "step": 45
    },
    {
      "epoch": 0.006891127673120857,
      "grad_norm": 0.5671194791793823,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.9264,
      "step": 46
    },
    {
      "epoch": 0.007040934796449571,
      "grad_norm": 0.6908413171768188,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.0477,
      "step": 47
    },
    {
      "epoch": 0.007190741919778285,
      "grad_norm": 0.7245323061943054,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9384,
      "step": 48
    },
    {
      "epoch": 0.007340549043107,
      "grad_norm": 0.9785915613174438,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.132,
      "step": 49
    },
    {
      "epoch": 0.007490356166435714,
      "grad_norm": 1.2804609537124634,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0875,
      "step": 50
    },
    {
      "epoch": 0.007490356166435714,
      "eval_loss": 0.8688188791275024,
      "eval_runtime": 568.3984,
      "eval_samples_per_second": 19.78,
      "eval_steps_per_second": 4.945,
      "step": 50
    },
    {
      "epoch": 0.007640163289764428,
      "grad_norm": 0.2369249016046524,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.8366,
      "step": 51
    },
    {
      "epoch": 0.007789970413093142,
      "grad_norm": 0.2243618369102478,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.7335,
      "step": 52
    },
    {
      "epoch": 0.007939777536421857,
      "grad_norm": 0.3180404305458069,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6498,
      "step": 53
    },
    {
      "epoch": 0.00808958465975057,
      "grad_norm": 0.3245214521884918,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8886,
      "step": 54
    },
    {
      "epoch": 0.008239391783079286,
      "grad_norm": 0.24352572858333588,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7486,
      "step": 55
    },
    {
      "epoch": 0.008389198906408,
      "grad_norm": 0.24336153268814087,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8348,
      "step": 56
    },
    {
      "epoch": 0.008539006029736713,
      "grad_norm": 0.2256353199481964,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8133,
      "step": 57
    },
    {
      "epoch": 0.008688813153065428,
      "grad_norm": 0.2895691692829132,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.874,
      "step": 58
    },
    {
      "epoch": 0.008838620276394142,
      "grad_norm": 0.2610842287540436,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8169,
      "step": 59
    },
    {
      "epoch": 0.008988427399722857,
      "grad_norm": 0.2484428733587265,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8387,
      "step": 60
    },
    {
      "epoch": 0.009138234523051571,
      "grad_norm": 0.23056460916996002,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.8971,
      "step": 61
    },
    {
      "epoch": 0.009288041646380285,
      "grad_norm": 0.24234654009342194,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7921,
      "step": 62
    },
    {
      "epoch": 0.009437848769709,
      "grad_norm": 0.22825555503368378,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8535,
      "step": 63
    },
    {
      "epoch": 0.009587655893037714,
      "grad_norm": 0.24779392778873444,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7923,
      "step": 64
    },
    {
      "epoch": 0.009737463016366429,
      "grad_norm": 0.2588535249233246,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7389,
      "step": 65
    },
    {
      "epoch": 0.009887270139695143,
      "grad_norm": 0.24879321455955505,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7638,
      "step": 66
    },
    {
      "epoch": 0.010037077263023856,
      "grad_norm": 0.2867943048477173,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8114,
      "step": 67
    },
    {
      "epoch": 0.010186884386352572,
      "grad_norm": 0.2666427493095398,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6136,
      "step": 68
    },
    {
      "epoch": 0.010336691509681285,
      "grad_norm": 0.2932893633842468,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9237,
      "step": 69
    },
    {
      "epoch": 0.010486498633009999,
      "grad_norm": 0.2577749788761139,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7551,
      "step": 70
    },
    {
      "epoch": 0.010636305756338714,
      "grad_norm": 0.2540102005004883,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7356,
      "step": 71
    },
    {
      "epoch": 0.010786112879667428,
      "grad_norm": 0.33452343940734863,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.6979,
      "step": 72
    },
    {
      "epoch": 0.010935920002996143,
      "grad_norm": 0.27727267146110535,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7675,
      "step": 73
    },
    {
      "epoch": 0.011085727126324857,
      "grad_norm": 0.2692679464817047,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7576,
      "step": 74
    },
    {
      "epoch": 0.01123553424965357,
      "grad_norm": 0.2856887876987457,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8196,
      "step": 75
    },
    {
      "epoch": 0.011385341372982286,
      "grad_norm": 0.2883060574531555,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.8396,
      "step": 76
    },
    {
      "epoch": 0.011535148496311,
      "grad_norm": 0.28473779559135437,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.8057,
      "step": 77
    },
    {
      "epoch": 0.011684955619639713,
      "grad_norm": 0.2777874171733856,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.6675,
      "step": 78
    },
    {
      "epoch": 0.011834762742968429,
      "grad_norm": 0.31093916296958923,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.9278,
      "step": 79
    },
    {
      "epoch": 0.011984569866297142,
      "grad_norm": 0.28080371022224426,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8478,
      "step": 80
    },
    {
      "epoch": 0.012134376989625857,
      "grad_norm": 0.2555106580257416,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.8204,
      "step": 81
    },
    {
      "epoch": 0.012284184112954571,
      "grad_norm": 0.29992347955703735,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.8931,
      "step": 82
    },
    {
      "epoch": 0.012433991236283285,
      "grad_norm": 0.2982628643512726,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7932,
      "step": 83
    },
    {
      "epoch": 0.012583798359612,
      "grad_norm": 0.29373466968536377,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.9268,
      "step": 84
    },
    {
      "epoch": 0.012733605482940714,
      "grad_norm": 0.32724693417549133,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8588,
      "step": 85
    },
    {
      "epoch": 0.012883412606269427,
      "grad_norm": 0.2967337667942047,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6942,
      "step": 86
    },
    {
      "epoch": 0.013033219729598143,
      "grad_norm": 0.35658177733421326,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7281,
      "step": 87
    },
    {
      "epoch": 0.013183026852926856,
      "grad_norm": 0.33493468165397644,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.8296,
      "step": 88
    },
    {
      "epoch": 0.013332833976255572,
      "grad_norm": 0.3347296118736267,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7777,
      "step": 89
    },
    {
      "epoch": 0.013482641099584285,
      "grad_norm": 0.3696501553058624,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8478,
      "step": 90
    },
    {
      "epoch": 0.013632448222912999,
      "grad_norm": 0.5119266510009766,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7589,
      "step": 91
    },
    {
      "epoch": 0.013782255346241714,
      "grad_norm": 0.5026902556419373,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8701,
      "step": 92
    },
    {
      "epoch": 0.013932062469570428,
      "grad_norm": 0.43266385793685913,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.8913,
      "step": 93
    },
    {
      "epoch": 0.014081869592899142,
      "grad_norm": 0.4305877983570099,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6905,
      "step": 94
    },
    {
      "epoch": 0.014231676716227857,
      "grad_norm": 0.43609902262687683,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7148,
      "step": 95
    },
    {
      "epoch": 0.01438148383955657,
      "grad_norm": 0.5080938339233398,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.0156,
      "step": 96
    },
    {
      "epoch": 0.014531290962885286,
      "grad_norm": 0.5817869901657104,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.1493,
      "step": 97
    },
    {
      "epoch": 0.014681098086214,
      "grad_norm": 0.9376845359802246,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0068,
      "step": 98
    },
    {
      "epoch": 0.014830905209542713,
      "grad_norm": 0.8120721578598022,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.0105,
      "step": 99
    },
    {
      "epoch": 0.014980712332871429,
      "grad_norm": 1.0948816537857056,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.0315,
      "step": 100
    },
    {
      "epoch": 0.014980712332871429,
      "eval_loss": 0.8477387428283691,
      "eval_runtime": 567.7372,
      "eval_samples_per_second": 19.803,
      "eval_steps_per_second": 4.951,
      "step": 100
    },
    {
      "epoch": 0.015130519456200142,
      "grad_norm": 0.21487335860729218,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8855,
      "step": 101
    },
    {
      "epoch": 0.015280326579528856,
      "grad_norm": 0.27073433995246887,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.78,
      "step": 102
    },
    {
      "epoch": 0.015430133702857571,
      "grad_norm": 0.22832012176513672,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5703,
      "step": 103
    },
    {
      "epoch": 0.015579940826186285,
      "grad_norm": 0.561996340751648,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8075,
      "step": 104
    },
    {
      "epoch": 0.015729747949515,
      "grad_norm": 0.21872995793819427,
      "learning_rate": 5e-05,
      "loss": 0.7439,
      "step": 105
    },
    {
      "epoch": 0.015879555072843714,
      "grad_norm": 0.23321197926998138,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9032,
      "step": 106
    },
    {
      "epoch": 0.016029362196172427,
      "grad_norm": 0.247480109333992,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.0497,
      "step": 107
    },
    {
      "epoch": 0.01617916931950114,
      "grad_norm": 0.22745971381664276,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.9326,
      "step": 108
    },
    {
      "epoch": 0.016328976442829858,
      "grad_norm": 0.21271130442619324,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.7486,
      "step": 109
    },
    {
      "epoch": 0.01647878356615857,
      "grad_norm": 0.26367267966270447,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.893,
      "step": 110
    },
    {
      "epoch": 0.016628590689487285,
      "grad_norm": 0.2798305153846741,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.883,
      "step": 111
    },
    {
      "epoch": 0.016778397812816,
      "grad_norm": 0.2146042287349701,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.9419,
      "step": 112
    },
    {
      "epoch": 0.016928204936144713,
      "grad_norm": 0.23173148930072784,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.891,
      "step": 113
    },
    {
      "epoch": 0.017078012059473426,
      "grad_norm": 0.24624301493167877,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.8058,
      "step": 114
    },
    {
      "epoch": 0.017227819182802143,
      "grad_norm": 0.28666770458221436,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.886,
      "step": 115
    },
    {
      "epoch": 0.017377626306130857,
      "grad_norm": 0.24581004679203033,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8011,
      "step": 116
    },
    {
      "epoch": 0.01752743342945957,
      "grad_norm": 0.25446394085884094,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8472,
      "step": 117
    },
    {
      "epoch": 0.017677240552788284,
      "grad_norm": 0.2756370007991791,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.6757,
      "step": 118
    },
    {
      "epoch": 0.017827047676116998,
      "grad_norm": 0.2860568165779114,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8502,
      "step": 119
    },
    {
      "epoch": 0.017976854799445715,
      "grad_norm": 0.3061371445655823,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7587,
      "step": 120
    },
    {
      "epoch": 0.01812666192277443,
      "grad_norm": 0.26677167415618896,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7358,
      "step": 121
    },
    {
      "epoch": 0.018276469046103142,
      "grad_norm": 0.27612438797950745,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8028,
      "step": 122
    },
    {
      "epoch": 0.018426276169431856,
      "grad_norm": 0.31821104884147644,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7335,
      "step": 123
    },
    {
      "epoch": 0.01857608329276057,
      "grad_norm": 0.2641538679599762,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7258,
      "step": 124
    },
    {
      "epoch": 0.018725890416089287,
      "grad_norm": 0.2742711007595062,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.8571,
      "step": 125
    },
    {
      "epoch": 0.018875697539418,
      "grad_norm": 0.28631827235221863,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.8037,
      "step": 126
    },
    {
      "epoch": 0.019025504662746714,
      "grad_norm": 0.2540627121925354,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.678,
      "step": 127
    },
    {
      "epoch": 0.019175311786075427,
      "grad_norm": 0.2871909439563751,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7392,
      "step": 128
    },
    {
      "epoch": 0.01932511890940414,
      "grad_norm": 0.28119537234306335,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6991,
      "step": 129
    },
    {
      "epoch": 0.019474926032732858,
      "grad_norm": 0.27180132269859314,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7025,
      "step": 130
    },
    {
      "epoch": 0.019624733156061572,
      "grad_norm": 0.2700372040271759,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8442,
      "step": 131
    },
    {
      "epoch": 0.019774540279390285,
      "grad_norm": 0.2593667507171631,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7101,
      "step": 132
    },
    {
      "epoch": 0.019924347402719,
      "grad_norm": 0.3013896048069,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8676,
      "step": 133
    },
    {
      "epoch": 0.020074154526047713,
      "grad_norm": 0.29744523763656616,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7809,
      "step": 134
    },
    {
      "epoch": 0.020223961649376426,
      "grad_norm": 0.29425275325775146,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.8395,
      "step": 135
    },
    {
      "epoch": 0.020373768772705143,
      "grad_norm": 0.290644109249115,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.8011,
      "step": 136
    },
    {
      "epoch": 0.020523575896033857,
      "grad_norm": 0.29827746748924255,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8402,
      "step": 137
    },
    {
      "epoch": 0.02067338301936257,
      "grad_norm": 0.2946103811264038,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7247,
      "step": 138
    },
    {
      "epoch": 0.020823190142691284,
      "grad_norm": 0.38548269867897034,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.8138,
      "step": 139
    },
    {
      "epoch": 0.020972997266019998,
      "grad_norm": 0.2995039224624634,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7435,
      "step": 140
    },
    {
      "epoch": 0.021122804389348715,
      "grad_norm": 0.3135714828968048,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7181,
      "step": 141
    },
    {
      "epoch": 0.02127261151267743,
      "grad_norm": 0.3725619912147522,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7686,
      "step": 142
    },
    {
      "epoch": 0.021422418636006142,
      "grad_norm": 0.41671574115753174,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7906,
      "step": 143
    },
    {
      "epoch": 0.021572225759334856,
      "grad_norm": 0.4549003839492798,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.9617,
      "step": 144
    },
    {
      "epoch": 0.02172203288266357,
      "grad_norm": 0.459332138299942,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.8265,
      "step": 145
    },
    {
      "epoch": 0.021871840005992287,
      "grad_norm": 0.47894296050071716,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.9195,
      "step": 146
    },
    {
      "epoch": 0.022021647129321,
      "grad_norm": 0.6261174082756042,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.025,
      "step": 147
    },
    {
      "epoch": 0.022171454252649714,
      "grad_norm": 0.9317310452461243,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.9746,
      "step": 148
    },
    {
      "epoch": 0.022321261375978427,
      "grad_norm": 1.1701384782791138,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.8404,
      "step": 149
    },
    {
      "epoch": 0.02247106849930714,
      "grad_norm": 1.098693609237671,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.9547,
      "step": 150
    },
    {
      "epoch": 0.02247106849930714,
      "eval_loss": 0.8422527313232422,
      "eval_runtime": 568.1109,
      "eval_samples_per_second": 19.79,
      "eval_steps_per_second": 4.948,
      "step": 150
    },
    {
      "epoch": 0.022620875622635855,
      "grad_norm": 0.18898192048072815,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.7215,
      "step": 151
    },
    {
      "epoch": 0.022770682745964572,
      "grad_norm": 0.2388179451227188,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6902,
      "step": 152
    },
    {
      "epoch": 0.022920489869293285,
      "grad_norm": 0.41913092136383057,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7113,
      "step": 153
    },
    {
      "epoch": 0.023070296992622,
      "grad_norm": 0.22527259588241577,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.6841,
      "step": 154
    },
    {
      "epoch": 0.023220104115950713,
      "grad_norm": 0.18967139720916748,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.8281,
      "step": 155
    },
    {
      "epoch": 0.023369911239279426,
      "grad_norm": 0.1980752944946289,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.7506,
      "step": 156
    },
    {
      "epoch": 0.023519718362608143,
      "grad_norm": 0.2360668182373047,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.9188,
      "step": 157
    },
    {
      "epoch": 0.023669525485936857,
      "grad_norm": 0.21157562732696533,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.9648,
      "step": 158
    },
    {
      "epoch": 0.02381933260926557,
      "grad_norm": 0.20437665283679962,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8487,
      "step": 159
    },
    {
      "epoch": 0.023969139732594284,
      "grad_norm": 0.20270663499832153,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7895,
      "step": 160
    },
    {
      "epoch": 0.024118946855922998,
      "grad_norm": 0.2236839085817337,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.9018,
      "step": 161
    },
    {
      "epoch": 0.024268753979251715,
      "grad_norm": 0.21588213741779327,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8231,
      "step": 162
    },
    {
      "epoch": 0.02441856110258043,
      "grad_norm": 0.22752077877521515,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8567,
      "step": 163
    },
    {
      "epoch": 0.024568368225909142,
      "grad_norm": 0.2827790379524231,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.8503,
      "step": 164
    },
    {
      "epoch": 0.024718175349237856,
      "grad_norm": 0.25776752829551697,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.6566,
      "step": 165
    },
    {
      "epoch": 0.02486798247256657,
      "grad_norm": 0.2566935420036316,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.8419,
      "step": 166
    },
    {
      "epoch": 0.025017789595895283,
      "grad_norm": 0.30715909600257874,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7849,
      "step": 167
    },
    {
      "epoch": 0.025167596719224,
      "grad_norm": 0.24969881772994995,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7011,
      "step": 168
    },
    {
      "epoch": 0.025317403842552714,
      "grad_norm": 0.2686540484428406,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7597,
      "step": 169
    },
    {
      "epoch": 0.025467210965881427,
      "grad_norm": 0.2643718719482422,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7392,
      "step": 170
    },
    {
      "epoch": 0.02561701808921014,
      "grad_norm": 0.2777179181575775,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.851,
      "step": 171
    },
    {
      "epoch": 0.025766825212538855,
      "grad_norm": 0.26481401920318604,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.631,
      "step": 172
    },
    {
      "epoch": 0.025916632335867572,
      "grad_norm": 0.2540353238582611,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.792,
      "step": 173
    },
    {
      "epoch": 0.026066439459196285,
      "grad_norm": 0.2759273052215576,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.9144,
      "step": 174
    },
    {
      "epoch": 0.026216246582525,
      "grad_norm": 0.2873280942440033,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.7864,
      "step": 175
    },
    {
      "epoch": 0.026366053705853713,
      "grad_norm": 0.2554738521575928,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6807,
      "step": 176
    },
    {
      "epoch": 0.026515860829182426,
      "grad_norm": 0.2898644506931305,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7932,
      "step": 177
    },
    {
      "epoch": 0.026665667952511143,
      "grad_norm": 0.2970656156539917,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7186,
      "step": 178
    },
    {
      "epoch": 0.026815475075839857,
      "grad_norm": 0.2831547260284424,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.8004,
      "step": 179
    },
    {
      "epoch": 0.02696528219916857,
      "grad_norm": 0.29099857807159424,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.7029,
      "step": 180
    },
    {
      "epoch": 0.027115089322497284,
      "grad_norm": 0.272522896528244,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7507,
      "step": 181
    },
    {
      "epoch": 0.027264896445825998,
      "grad_norm": 0.29832085967063904,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.9112,
      "step": 182
    },
    {
      "epoch": 0.027414703569154715,
      "grad_norm": 0.2714107632637024,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.8058,
      "step": 183
    },
    {
      "epoch": 0.02756451069248343,
      "grad_norm": 0.2914239764213562,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7447,
      "step": 184
    },
    {
      "epoch": 0.027714317815812142,
      "grad_norm": 0.296657532453537,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.8355,
      "step": 185
    },
    {
      "epoch": 0.027864124939140856,
      "grad_norm": 0.27173134684562683,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.7745,
      "step": 186
    },
    {
      "epoch": 0.02801393206246957,
      "grad_norm": 0.3543894290924072,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.9567,
      "step": 187
    },
    {
      "epoch": 0.028163739185798283,
      "grad_norm": 0.3419502377510071,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.828,
      "step": 188
    },
    {
      "epoch": 0.028313546309127,
      "grad_norm": 0.35001078248023987,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8224,
      "step": 189
    },
    {
      "epoch": 0.028463353432455714,
      "grad_norm": 0.3231000006198883,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.726,
      "step": 190
    },
    {
      "epoch": 0.028613160555784427,
      "grad_norm": 0.43736642599105835,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.8406,
      "step": 191
    },
    {
      "epoch": 0.02876296767911314,
      "grad_norm": 0.4133260250091553,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.8529,
      "step": 192
    },
    {
      "epoch": 0.028912774802441855,
      "grad_norm": 0.3894733190536499,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7316,
      "step": 193
    },
    {
      "epoch": 0.029062581925770572,
      "grad_norm": 0.4218355417251587,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8377,
      "step": 194
    },
    {
      "epoch": 0.029212389049099285,
      "grad_norm": 0.4262062907218933,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.0527,
      "step": 195
    },
    {
      "epoch": 0.029362196172428,
      "grad_norm": 0.48938897252082825,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.0953,
      "step": 196
    },
    {
      "epoch": 0.029512003295756713,
      "grad_norm": 0.5830502510070801,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.0599,
      "step": 197
    },
    {
      "epoch": 0.029661810419085426,
      "grad_norm": 0.6355454921722412,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.9897,
      "step": 198
    },
    {
      "epoch": 0.029811617542414143,
      "grad_norm": 0.7947019338607788,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.12,
      "step": 199
    },
    {
      "epoch": 0.029961424665742857,
      "grad_norm": 1.0451745986938477,
      "learning_rate": 0.0,
      "loss": 0.9059,
      "step": 200
    },
    {
      "epoch": 0.029961424665742857,
      "eval_loss": 0.8421279191970825,
      "eval_runtime": 568.7717,
      "eval_samples_per_second": 19.767,
      "eval_steps_per_second": 4.942,
      "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": 1.2221066769963418e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}