{
  "best_metric": 0.7737080454826355,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.006646704397791965,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.329340879558393e-05,
      "grad_norm": 0.5352020859718323,
      "learning_rate": 5e-06,
      "loss": 1.2089,
      "step": 1
    },
    {
      "epoch": 1.329340879558393e-05,
      "eval_loss": 1.9079885482788086,
      "eval_runtime": 5375.4948,
      "eval_samples_per_second": 23.569,
      "eval_steps_per_second": 5.892,
      "step": 1
    },
    {
      "epoch": 2.658681759116786e-05,
      "grad_norm": 1.0845952033996582,
      "learning_rate": 1e-05,
      "loss": 1.2448,
      "step": 2
    },
    {
      "epoch": 3.988022638675179e-05,
      "grad_norm": 0.8397296071052551,
      "learning_rate": 1.5e-05,
      "loss": 1.1859,
      "step": 3
    },
    {
      "epoch": 5.317363518233572e-05,
      "grad_norm": 0.8907555341720581,
      "learning_rate": 2e-05,
      "loss": 1.1424,
      "step": 4
    },
    {
      "epoch": 6.646704397791965e-05,
      "grad_norm": 0.9167027473449707,
      "learning_rate": 2.5e-05,
      "loss": 1.223,
      "step": 5
    },
    {
      "epoch": 7.976045277350358e-05,
      "grad_norm": 0.977672815322876,
      "learning_rate": 3e-05,
      "loss": 1.1752,
      "step": 6
    },
    {
      "epoch": 9.305386156908751e-05,
      "grad_norm": 1.1303290128707886,
      "learning_rate": 3.5e-05,
      "loss": 1.2163,
      "step": 7
    },
    {
      "epoch": 0.00010634727036467144,
      "grad_norm": 0.8967212438583374,
      "learning_rate": 4e-05,
      "loss": 1.172,
      "step": 8
    },
    {
      "epoch": 0.00011964067916025536,
      "grad_norm": 0.8516184687614441,
      "learning_rate": 4.5e-05,
      "loss": 1.1063,
      "step": 9
    },
    {
      "epoch": 0.0001329340879558393,
      "grad_norm": 1.0285944938659668,
      "learning_rate": 5e-05,
      "loss": 1.164,
      "step": 10
    },
    {
      "epoch": 0.00014622749675142322,
      "grad_norm": 1.19761061668396,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.1598,
      "step": 11
    },
    {
      "epoch": 0.00015952090554700716,
      "grad_norm": 1.2036720514297485,
      "learning_rate": 6e-05,
      "loss": 1.231,
      "step": 12
    },
    {
      "epoch": 0.00017281431434259108,
      "grad_norm": 0.898175060749054,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.1002,
      "step": 13
    },
    {
      "epoch": 0.00018610772313817502,
      "grad_norm": 1.2640652656555176,
      "learning_rate": 7e-05,
      "loss": 1.0669,
      "step": 14
    },
    {
      "epoch": 0.00019940113193375893,
      "grad_norm": 1.567511796951294,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0288,
      "step": 15
    },
    {
      "epoch": 0.00021269454072934287,
      "grad_norm": 1.2289221286773682,
      "learning_rate": 8e-05,
      "loss": 0.9291,
      "step": 16
    },
    {
      "epoch": 0.00022598794952492681,
      "grad_norm": 0.9787936806678772,
      "learning_rate": 8.5e-05,
      "loss": 0.9272,
      "step": 17
    },
    {
      "epoch": 0.00023928135832051073,
      "grad_norm": 1.1664317846298218,
      "learning_rate": 9e-05,
      "loss": 0.8936,
      "step": 18
    },
    {
      "epoch": 0.00025257476711609464,
      "grad_norm": 1.3458384275436401,
      "learning_rate": 9.5e-05,
      "loss": 0.879,
      "step": 19
    },
    {
      "epoch": 0.0002658681759116786,
      "grad_norm": 1.0688328742980957,
      "learning_rate": 0.0001,
      "loss": 0.9404,
      "step": 20
    },
    {
      "epoch": 0.0002791615847072625,
      "grad_norm": 1.3917220830917358,
      "learning_rate": 9.999892908320647e-05,
      "loss": 0.8472,
      "step": 21
    },
    {
      "epoch": 0.00029245499350284644,
      "grad_norm": 1.3215646743774414,
      "learning_rate": 9.999571637870036e-05,
      "loss": 0.8114,
      "step": 22
    },
    {
      "epoch": 0.00030574840229843035,
      "grad_norm": 1.2741371393203735,
      "learning_rate": 9.999036202410325e-05,
      "loss": 0.8859,
      "step": 23
    },
    {
      "epoch": 0.0003190418110940143,
      "grad_norm": 1.1992707252502441,
      "learning_rate": 9.998286624877786e-05,
      "loss": 0.8252,
      "step": 24
    },
    {
      "epoch": 0.00033233521988959824,
      "grad_norm": 1.4191838502883911,
      "learning_rate": 9.997322937381829e-05,
      "loss": 0.7696,
      "step": 25
    },
    {
      "epoch": 0.00034562862868518215,
      "grad_norm": 1.3826225996017456,
      "learning_rate": 9.996145181203615e-05,
      "loss": 1.034,
      "step": 26
    },
    {
      "epoch": 0.0003589220374807661,
      "grad_norm": 1.5673127174377441,
      "learning_rate": 9.994753406794301e-05,
      "loss": 0.6459,
      "step": 27
    },
    {
      "epoch": 0.00037221544627635004,
      "grad_norm": 1.3654550313949585,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.8892,
      "step": 28
    },
    {
      "epoch": 0.00038550885507193395,
      "grad_norm": 1.8788448572158813,
      "learning_rate": 9.991328050923581e-05,
      "loss": 0.8865,
      "step": 29
    },
    {
      "epoch": 0.00039880226386751786,
      "grad_norm": 1.5875370502471924,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.78,
      "step": 30
    },
    {
      "epoch": 0.00041209567266310183,
      "grad_norm": 1.2988790273666382,
      "learning_rate": 9.98704745668676e-05,
      "loss": 0.8883,
      "step": 31
    },
    {
      "epoch": 0.00042538908145868575,
      "grad_norm": 1.6404173374176025,
      "learning_rate": 9.98458666866564e-05,
      "loss": 0.9873,
      "step": 32
    },
    {
      "epoch": 0.00043868249025426966,
      "grad_norm": 1.5195177793502808,
      "learning_rate": 9.981912357541627e-05,
      "loss": 0.7668,
      "step": 33
    },
    {
      "epoch": 0.00045197589904985363,
      "grad_norm": 1.656965732574463,
      "learning_rate": 9.97902463787331e-05,
      "loss": 1.0288,
      "step": 34
    },
    {
      "epoch": 0.00046526930784543754,
      "grad_norm": 1.593886137008667,
      "learning_rate": 9.975923633360985e-05,
      "loss": 1.0363,
      "step": 35
    },
    {
      "epoch": 0.00047856271664102146,
      "grad_norm": 1.5617332458496094,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.9738,
      "step": 36
    },
    {
      "epoch": 0.0004918561254366054,
      "grad_norm": 1.511904001235962,
      "learning_rate": 9.969082310281891e-05,
      "loss": 0.7352,
      "step": 37
    },
    {
      "epoch": 0.0005051495342321893,
      "grad_norm": 1.5485260486602783,
      "learning_rate": 9.965342284774632e-05,
      "loss": 0.7795,
      "step": 38
    },
    {
      "epoch": 0.0005184429430277732,
      "grad_norm": 1.3302539587020874,
      "learning_rate": 9.961389560529836e-05,
      "loss": 0.7829,
      "step": 39
    },
    {
      "epoch": 0.0005317363518233572,
      "grad_norm": 1.6533401012420654,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.8549,
      "step": 40
    },
    {
      "epoch": 0.0005450297606189411,
      "grad_norm": 2.1486949920654297,
      "learning_rate": 9.952846702217886e-05,
      "loss": 0.8375,
      "step": 41
    },
    {
      "epoch": 0.000558323169414525,
      "grad_norm": 1.608331561088562,
      "learning_rate": 9.948256934098352e-05,
      "loss": 0.9182,
      "step": 42
    },
    {
      "epoch": 0.000571616578210109,
      "grad_norm": 1.4748098850250244,
      "learning_rate": 9.943455199120837e-05,
      "loss": 0.6944,
      "step": 43
    },
    {
      "epoch": 0.0005849099870056929,
      "grad_norm": 1.9486955404281616,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.016,
      "step": 44
    },
    {
      "epoch": 0.0005982033958012768,
      "grad_norm": 1.963842749595642,
      "learning_rate": 9.933216660424395e-05,
      "loss": 0.8257,
      "step": 45
    },
    {
      "epoch": 0.0006114968045968607,
      "grad_norm": 2.1671032905578613,
      "learning_rate": 9.927780295290389e-05,
      "loss": 0.8887,
      "step": 46
    },
    {
      "epoch": 0.0006247902133924447,
      "grad_norm": 2.2479171752929688,
      "learning_rate": 9.922132840449459e-05,
      "loss": 0.9081,
      "step": 47
    },
    {
      "epoch": 0.0006380836221880286,
      "grad_norm": 2.173774480819702,
      "learning_rate": 9.916274537819775e-05,
      "loss": 0.912,
      "step": 48
    },
    {
      "epoch": 0.0006513770309836126,
      "grad_norm": 2.9918084144592285,
      "learning_rate": 9.91020563835152e-05,
      "loss": 0.9588,
      "step": 49
    },
    {
      "epoch": 0.0006646704397791965,
      "grad_norm": 3.5322818756103516,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.0024,
      "step": 50
    },
    {
      "epoch": 0.0006779638485747804,
      "grad_norm": 1.3917131423950195,
      "learning_rate": 9.897437097795257e-05,
      "loss": 1.1615,
      "step": 51
    },
    {
      "epoch": 0.0006912572573703643,
      "grad_norm": 1.1273274421691895,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.0447,
      "step": 52
    },
    {
      "epoch": 0.0007045506661659482,
      "grad_norm": 1.1798847913742065,
      "learning_rate": 9.883829406604363e-05,
      "loss": 0.992,
      "step": 53
    },
    {
      "epoch": 0.0007178440749615322,
      "grad_norm": 0.9056446552276611,
      "learning_rate": 9.876711602542563e-05,
      "loss": 0.783,
      "step": 54
    },
    {
      "epoch": 0.0007311374837571162,
      "grad_norm": 0.9748833775520325,
      "learning_rate": 9.869384896386668e-05,
      "loss": 0.9052,
      "step": 55
    },
    {
      "epoch": 0.0007444308925527001,
      "grad_norm": 0.7025169730186462,
      "learning_rate": 9.861849601988383e-05,
      "loss": 0.8526,
      "step": 56
    },
    {
      "epoch": 0.000757724301348284,
      "grad_norm": 0.743742048740387,
      "learning_rate": 9.854106042134641e-05,
      "loss": 0.8399,
      "step": 57
    },
    {
      "epoch": 0.0007710177101438679,
      "grad_norm": 0.7727916836738586,
      "learning_rate": 9.846154548533773e-05,
      "loss": 1.0684,
      "step": 58
    },
    {
      "epoch": 0.0007843111189394518,
      "grad_norm": 0.842779815196991,
      "learning_rate": 9.837995461801299e-05,
      "loss": 0.7662,
      "step": 59
    },
    {
      "epoch": 0.0007976045277350357,
      "grad_norm": 0.9934501051902771,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.7445,
      "step": 60
    },
    {
      "epoch": 0.0008108979365306198,
      "grad_norm": 0.7703706622123718,
      "learning_rate": 9.821055915851647e-05,
      "loss": 0.9886,
      "step": 61
    },
    {
      "epoch": 0.0008241913453262037,
      "grad_norm": 0.9399131536483765,
      "learning_rate": 9.812276182268236e-05,
      "loss": 1.0003,
      "step": 62
    },
    {
      "epoch": 0.0008374847541217876,
      "grad_norm": 0.8626309037208557,
      "learning_rate": 9.803290306789676e-05,
      "loss": 0.8059,
      "step": 63
    },
    {
      "epoch": 0.0008507781629173715,
      "grad_norm": 0.7753542065620422,
      "learning_rate": 9.794098674340965e-05,
      "loss": 0.9001,
      "step": 64
    },
    {
      "epoch": 0.0008640715717129554,
      "grad_norm": 0.8867607712745667,
      "learning_rate": 9.784701678661045e-05,
      "loss": 0.9717,
      "step": 65
    },
    {
      "epoch": 0.0008773649805085393,
      "grad_norm": 1.0961718559265137,
      "learning_rate": 9.775099722285935e-05,
      "loss": 0.8779,
      "step": 66
    },
    {
      "epoch": 0.0008906583893041232,
      "grad_norm": 0.8895187377929688,
      "learning_rate": 9.765293216531486e-05,
      "loss": 0.8501,
      "step": 67
    },
    {
      "epoch": 0.0009039517980997073,
      "grad_norm": 0.8074072599411011,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9009,
      "step": 68
    },
    {
      "epoch": 0.0009172452068952912,
      "grad_norm": 0.8209161162376404,
      "learning_rate": 9.74506824594107e-05,
      "loss": 0.8622,
      "step": 69
    },
    {
      "epoch": 0.0009305386156908751,
      "grad_norm": 0.9414666891098022,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.7904,
      "step": 70
    },
    {
      "epoch": 0.000943832024486459,
      "grad_norm": 0.8673354983329773,
      "learning_rate": 9.724030232334391e-05,
      "loss": 0.9061,
      "step": 71
    },
    {
      "epoch": 0.0009571254332820429,
      "grad_norm": 0.9704405665397644,
      "learning_rate": 9.713207455460894e-05,
      "loss": 1.0696,
      "step": 72
    },
    {
      "epoch": 0.0009704188420776268,
      "grad_norm": 0.9599660038948059,
      "learning_rate": 9.702182780466775e-05,
      "loss": 0.7631,
      "step": 73
    },
    {
      "epoch": 0.0009837122508732107,
      "grad_norm": 0.9537084102630615,
      "learning_rate": 9.690956679612421e-05,
      "loss": 0.7974,
      "step": 74
    },
    {
      "epoch": 0.0009970056596687947,
      "grad_norm": 0.8513907790184021,
      "learning_rate": 9.67952963378663e-05,
      "loss": 0.9262,
      "step": 75
    },
    {
      "epoch": 0.0010102990684643786,
      "grad_norm": 1.0655099153518677,
      "learning_rate": 9.667902132486009e-05,
      "loss": 0.894,
      "step": 76
    },
    {
      "epoch": 0.0010235924772599625,
      "grad_norm": 1.2117468118667603,
      "learning_rate": 9.656074673794018e-05,
      "loss": 0.8309,
      "step": 77
    },
    {
      "epoch": 0.0010368858860555464,
      "grad_norm": 1.2190030813217163,
      "learning_rate": 9.644047764359622e-05,
      "loss": 0.7741,
      "step": 78
    },
    {
      "epoch": 0.0010501792948511305,
      "grad_norm": 1.2191436290740967,
      "learning_rate": 9.631821919375591e-05,
      "loss": 0.8216,
      "step": 79
    },
    {
      "epoch": 0.0010634727036467144,
      "grad_norm": 0.9901348948478699,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.7465,
      "step": 80
    },
    {
      "epoch": 0.0010767661124422984,
      "grad_norm": 0.9281037449836731,
      "learning_rate": 9.606775526115963e-05,
      "loss": 0.8045,
      "step": 81
    },
    {
      "epoch": 0.0010900595212378823,
      "grad_norm": 0.995185136795044,
      "learning_rate": 9.593956050744492e-05,
      "loss": 0.7302,
      "step": 82
    },
    {
      "epoch": 0.0011033529300334662,
      "grad_norm": 1.1214485168457031,
      "learning_rate": 9.580939785585681e-05,
      "loss": 0.9075,
      "step": 83
    },
    {
      "epoch": 0.00111664633882905,
      "grad_norm": 1.0287375450134277,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.8475,
      "step": 84
    },
    {
      "epoch": 0.001129939747624634,
      "grad_norm": 1.3222854137420654,
      "learning_rate": 9.554319124605879e-05,
      "loss": 0.7471,
      "step": 85
    },
    {
      "epoch": 0.001143233156420218,
      "grad_norm": 1.1217132806777954,
      "learning_rate": 9.540715869125407e-05,
      "loss": 0.6725,
      "step": 86
    },
    {
      "epoch": 0.0011565265652158018,
      "grad_norm": 1.1724450588226318,
      "learning_rate": 9.526918104489777e-05,
      "loss": 0.7773,
      "step": 87
    },
    {
      "epoch": 0.0011698199740113858,
      "grad_norm": 1.2220860719680786,
      "learning_rate": 9.512926421749304e-05,
      "loss": 0.6838,
      "step": 88
    },
    {
      "epoch": 0.0011831133828069697,
      "grad_norm": 1.4272316694259644,
      "learning_rate": 9.498741420261108e-05,
      "loss": 0.7358,
      "step": 89
    },
    {
      "epoch": 0.0011964067916025536,
      "grad_norm": 1.3407106399536133,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.6635,
      "step": 90
    },
    {
      "epoch": 0.0012097002003981375,
      "grad_norm": 1.4183844327926636,
      "learning_rate": 9.469793899849661e-05,
      "loss": 0.7953,
      "step": 91
    },
    {
      "epoch": 0.0012229936091937214,
      "grad_norm": 1.2790828943252563,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.6168,
      "step": 92
    },
    {
      "epoch": 0.0012362870179893056,
      "grad_norm": 1.5876028537750244,
      "learning_rate": 9.440080503264037e-05,
      "loss": 0.6267,
      "step": 93
    },
    {
      "epoch": 0.0012495804267848895,
      "grad_norm": 1.8595623970031738,
      "learning_rate": 9.42493818731521e-05,
      "loss": 0.7267,
      "step": 94
    },
    {
      "epoch": 0.0012628738355804734,
      "grad_norm": 2.025190830230713,
      "learning_rate": 9.409606321741775e-05,
      "loss": 0.9919,
      "step": 95
    },
    {
      "epoch": 0.0012761672443760573,
      "grad_norm": 1.9461756944656372,
      "learning_rate": 9.394085563309827e-05,
      "loss": 0.9334,
      "step": 96
    },
    {
      "epoch": 0.0012894606531716412,
      "grad_norm": 1.8210233449935913,
      "learning_rate": 9.378376576876999e-05,
      "loss": 0.6643,
      "step": 97
    },
    {
      "epoch": 0.0013027540619672251,
      "grad_norm": 2.0528371334075928,
      "learning_rate": 9.362480035363986e-05,
      "loss": 0.7994,
      "step": 98
    },
    {
      "epoch": 0.001316047470762809,
      "grad_norm": 1.7985663414001465,
      "learning_rate": 9.34639661972572e-05,
      "loss": 0.7684,
      "step": 99
    },
    {
      "epoch": 0.001329340879558393,
      "grad_norm": 3.4086496829986572,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.8968,
      "step": 100
    },
    {
      "epoch": 0.001329340879558393,
      "eval_loss": 0.8801698684692383,
      "eval_runtime": 5386.8725,
      "eval_samples_per_second": 23.519,
      "eval_steps_per_second": 5.88,
      "step": 100
    },
    {
      "epoch": 0.0013426342883539769,
      "grad_norm": 0.8081527948379517,
      "learning_rate": 9.31367192988896e-05,
      "loss": 1.0367,
      "step": 101
    },
    {
      "epoch": 0.0013559276971495608,
      "grad_norm": 0.869454562664032,
      "learning_rate": 9.297032057507264e-05,
      "loss": 0.9744,
      "step": 102
    },
    {
      "epoch": 0.0013692211059451447,
      "grad_norm": 0.8773592710494995,
      "learning_rate": 9.280208114573859e-05,
      "loss": 0.9307,
      "step": 103
    },
    {
      "epoch": 0.0013825145147407286,
      "grad_norm": 0.7954993844032288,
      "learning_rate": 9.263200821770461e-05,
      "loss": 1.0105,
      "step": 104
    },
    {
      "epoch": 0.0013958079235363125,
      "grad_norm": 0.7065267562866211,
      "learning_rate": 9.246010907632895e-05,
      "loss": 0.9174,
      "step": 105
    },
    {
      "epoch": 0.0014091013323318964,
      "grad_norm": 0.6152194142341614,
      "learning_rate": 9.228639108519868e-05,
      "loss": 0.8309,
      "step": 106
    },
    {
      "epoch": 0.0014223947411274806,
      "grad_norm": 0.7067243456840515,
      "learning_rate": 9.211086168581433e-05,
      "loss": 0.8691,
      "step": 107
    },
    {
      "epoch": 0.0014356881499230645,
      "grad_norm": 0.6619918346405029,
      "learning_rate": 9.193352839727121e-05,
      "loss": 1.0272,
      "step": 108
    },
    {
      "epoch": 0.0014489815587186484,
      "grad_norm": 0.7928242087364197,
      "learning_rate": 9.175439881593716e-05,
      "loss": 0.896,
      "step": 109
    },
    {
      "epoch": 0.0014622749675142323,
      "grad_norm": 0.8225681185722351,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.8918,
      "step": 110
    },
    {
      "epoch": 0.0014755683763098162,
      "grad_norm": 0.7953227162361145,
      "learning_rate": 9.139078154477512e-05,
      "loss": 0.8082,
      "step": 111
    },
    {
      "epoch": 0.0014888617851054001,
      "grad_norm": 0.811774492263794,
      "learning_rate": 9.120630943110077e-05,
      "loss": 0.7503,
      "step": 112
    },
    {
      "epoch": 0.001502155193900984,
      "grad_norm": 0.8218790888786316,
      "learning_rate": 9.102007217627568e-05,
      "loss": 0.8041,
      "step": 113
    },
    {
      "epoch": 0.001515448602696568,
      "grad_norm": 0.8435613512992859,
      "learning_rate": 9.083207775808396e-05,
      "loss": 0.8582,
      "step": 114
    },
    {
      "epoch": 0.0015287420114921519,
      "grad_norm": 0.7614986300468445,
      "learning_rate": 9.064233422958077e-05,
      "loss": 1.0296,
      "step": 115
    },
    {
      "epoch": 0.0015420354202877358,
      "grad_norm": 0.8620554208755493,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8751,
      "step": 116
    },
    {
      "epoch": 0.0015553288290833197,
      "grad_norm": 1.0255271196365356,
      "learning_rate": 9.025763242814291e-05,
      "loss": 0.8303,
      "step": 117
    },
    {
      "epoch": 0.0015686222378789036,
      "grad_norm": 0.8680163621902466,
      "learning_rate": 9.006269063455304e-05,
      "loss": 0.8217,
      "step": 118
    },
    {
      "epoch": 0.0015819156466744875,
      "grad_norm": 0.9762370586395264,
      "learning_rate": 8.986603268863536e-05,
      "loss": 0.8599,
      "step": 119
    },
    {
      "epoch": 0.0015952090554700715,
      "grad_norm": 0.93663489818573,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.7959,
      "step": 120
    },
    {
      "epoch": 0.0016085024642656556,
      "grad_norm": 1.062989354133606,
      "learning_rate": 8.94676021096575e-05,
      "loss": 0.8412,
      "step": 121
    },
    {
      "epoch": 0.0016217958730612395,
      "grad_norm": 0.8994033336639404,
      "learning_rate": 8.926584654403724e-05,
      "loss": 0.659,
      "step": 122
    },
    {
      "epoch": 0.0016350892818568234,
      "grad_norm": 1.0036351680755615,
      "learning_rate": 8.906240896023794e-05,
      "loss": 0.8501,
      "step": 123
    },
    {
      "epoch": 0.0016483826906524073,
      "grad_norm": 0.897975504398346,
      "learning_rate": 8.885729807284856e-05,
      "loss": 0.9076,
      "step": 124
    },
    {
      "epoch": 0.0016616760994479912,
      "grad_norm": 1.0326918363571167,
      "learning_rate": 8.865052266813685e-05,
      "loss": 0.8129,
      "step": 125
    },
    {
      "epoch": 0.0016749695082435752,
      "grad_norm": 1.158320665359497,
      "learning_rate": 8.844209160367299e-05,
      "loss": 0.8412,
      "step": 126
    },
    {
      "epoch": 0.001688262917039159,
      "grad_norm": 1.188408374786377,
      "learning_rate": 8.823201380795001e-05,
      "loss": 0.7788,
      "step": 127
    },
    {
      "epoch": 0.001701556325834743,
      "grad_norm": 1.0547311305999756,
      "learning_rate": 8.802029828000156e-05,
      "loss": 0.749,
      "step": 128
    },
    {
      "epoch": 0.001714849734630327,
      "grad_norm": 1.0959973335266113,
      "learning_rate": 8.780695408901613e-05,
      "loss": 0.9506,
      "step": 129
    },
    {
      "epoch": 0.0017281431434259108,
      "grad_norm": 1.138036847114563,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.8127,
      "step": 130
    },
    {
      "epoch": 0.0017414365522214947,
      "grad_norm": 1.2309755086898804,
      "learning_rate": 8.737541634312985e-05,
      "loss": 0.8512,
      "step": 131
    },
    {
      "epoch": 0.0017547299610170786,
      "grad_norm": 1.073636531829834,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.8831,
      "step": 132
    },
    {
      "epoch": 0.0017680233698126626,
      "grad_norm": 0.9688912630081177,
      "learning_rate": 8.693747451206232e-05,
      "loss": 0.8654,
      "step": 133
    },
    {
      "epoch": 0.0017813167786082465,
      "grad_norm": 1.1723618507385254,
      "learning_rate": 8.671612547178428e-05,
      "loss": 0.9584,
      "step": 134
    },
    {
      "epoch": 0.0017946101874038306,
      "grad_norm": 1.1531357765197754,
      "learning_rate": 8.649320363489179e-05,
      "loss": 0.7535,
      "step": 135
    },
    {
      "epoch": 0.0018079035961994145,
      "grad_norm": 1.0542341470718384,
      "learning_rate": 8.626871855061438e-05,
      "loss": 0.727,
      "step": 136
    },
    {
      "epoch": 0.0018211970049949984,
      "grad_norm": 1.2966911792755127,
      "learning_rate": 8.604267983514594e-05,
      "loss": 0.8247,
      "step": 137
    },
    {
      "epoch": 0.0018344904137905823,
      "grad_norm": 1.119239091873169,
      "learning_rate": 8.581509717123273e-05,
      "loss": 0.7151,
      "step": 138
    },
    {
      "epoch": 0.0018477838225861663,
      "grad_norm": 1.548149585723877,
      "learning_rate": 8.558598030775857e-05,
      "loss": 0.9444,
      "step": 139
    },
    {
      "epoch": 0.0018610772313817502,
      "grad_norm": 1.794958233833313,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8175,
      "step": 140
    },
    {
      "epoch": 0.001874370640177334,
      "grad_norm": 1.7219867706298828,
      "learning_rate": 8.51231833058426e-05,
      "loss": 0.8264,
      "step": 141
    },
    {
      "epoch": 0.001887664048972918,
      "grad_norm": 1.3154703378677368,
      "learning_rate": 8.488952299208401e-05,
      "loss": 0.7259,
      "step": 142
    },
    {
      "epoch": 0.001900957457768502,
      "grad_norm": 1.3594454526901245,
      "learning_rate": 8.46543681272818e-05,
      "loss": 0.8234,
      "step": 143
    },
    {
      "epoch": 0.0019142508665640858,
      "grad_norm": 1.557629942893982,
      "learning_rate": 8.44177287846877e-05,
      "loss": 0.8365,
      "step": 144
    },
    {
      "epoch": 0.0019275442753596697,
      "grad_norm": 2.3887617588043213,
      "learning_rate": 8.417961510114356e-05,
      "loss": 0.747,
      "step": 145
    },
    {
      "epoch": 0.0019408376841552537,
      "grad_norm": 1.7031996250152588,
      "learning_rate": 8.39400372766471e-05,
      "loss": 0.8081,
      "step": 146
    },
    {
      "epoch": 0.0019541310929508376,
      "grad_norm": 1.5554150342941284,
      "learning_rate": 8.36990055739149e-05,
      "loss": 0.8215,
      "step": 147
    },
    {
      "epoch": 0.0019674245017464215,
      "grad_norm": 1.886732578277588,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.7777,
      "step": 148
    },
    {
      "epoch": 0.0019807179105420054,
      "grad_norm": 2.3210175037384033,
      "learning_rate": 8.321262189556409e-05,
      "loss": 0.9041,
      "step": 149
    },
    {
      "epoch": 0.0019940113193375893,
      "grad_norm": 2.9988458156585693,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.7906,
      "step": 150
    },
    {
      "epoch": 0.0020073047281331732,
      "grad_norm": 0.5462431311607361,
      "learning_rate": 8.272054740543052e-05,
      "loss": 1.029,
      "step": 151
    },
    {
      "epoch": 0.002020598136928757,
      "grad_norm": 0.7611443400382996,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.8637,
      "step": 152
    },
    {
      "epoch": 0.002033891545724341,
      "grad_norm": 0.6770411133766174,
      "learning_rate": 8.222286641794488e-05,
      "loss": 0.8939,
      "step": 153
    },
    {
      "epoch": 0.002047184954519925,
      "grad_norm": 0.749485969543457,
      "learning_rate": 8.197195009902924e-05,
      "loss": 0.8756,
      "step": 154
    },
    {
      "epoch": 0.002060478363315509,
      "grad_norm": 0.7469431757926941,
      "learning_rate": 8.171966420818228e-05,
      "loss": 0.9132,
      "step": 155
    },
    {
      "epoch": 0.002073771772111093,
      "grad_norm": 0.7187756299972534,
      "learning_rate": 8.146601955249188e-05,
      "loss": 0.8168,
      "step": 156
    },
    {
      "epoch": 0.002087065180906677,
      "grad_norm": 0.7999608516693115,
      "learning_rate": 8.121102699725089e-05,
      "loss": 0.8515,
      "step": 157
    },
    {
      "epoch": 0.002100358589702261,
      "grad_norm": 0.6854503154754639,
      "learning_rate": 8.095469746549172e-05,
      "loss": 0.8445,
      "step": 158
    },
    {
      "epoch": 0.002113651998497845,
      "grad_norm": 0.6535181999206543,
      "learning_rate": 8.069704193751832e-05,
      "loss": 0.9783,
      "step": 159
    },
    {
      "epoch": 0.002126945407293429,
      "grad_norm": 0.6873290538787842,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.907,
      "step": 160
    },
    {
      "epoch": 0.002140238816089013,
      "grad_norm": 1.005398154258728,
      "learning_rate": 8.017779709767858e-05,
      "loss": 0.9542,
      "step": 161
    },
    {
      "epoch": 0.0021535322248845967,
      "grad_norm": 0.7459506988525391,
      "learning_rate": 7.991623002853296e-05,
      "loss": 0.8161,
      "step": 162
    },
    {
      "epoch": 0.0021668256336801806,
      "grad_norm": 0.9030553698539734,
      "learning_rate": 7.965338144766186e-05,
      "loss": 0.8912,
      "step": 163
    },
    {
      "epoch": 0.0021801190424757646,
      "grad_norm": 0.7825924754142761,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.9259,
      "step": 164
    },
    {
      "epoch": 0.0021934124512713485,
      "grad_norm": 0.7606608271598816,
      "learning_rate": 7.912388484339012e-05,
      "loss": 0.8277,
      "step": 165
    },
    {
      "epoch": 0.0022067058600669324,
      "grad_norm": 0.9173434376716614,
      "learning_rate": 7.88572595018617e-05,
      "loss": 0.7893,
      "step": 166
    },
    {
      "epoch": 0.0022199992688625163,
      "grad_norm": 0.842113196849823,
      "learning_rate": 7.858939801138061e-05,
      "loss": 0.992,
      "step": 167
    },
    {
      "epoch": 0.0022332926776581,
      "grad_norm": 0.8527581691741943,
      "learning_rate": 7.832031184624164e-05,
      "loss": 0.8826,
      "step": 168
    },
    {
      "epoch": 0.002246586086453684,
      "grad_norm": 0.8675350546836853,
      "learning_rate": 7.80500125332005e-05,
      "loss": 0.9287,
      "step": 169
    },
    {
      "epoch": 0.002259879495249268,
      "grad_norm": 0.8264341354370117,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.949,
      "step": 170
    },
    {
      "epoch": 0.002273172904044852,
      "grad_norm": 0.8730234503746033,
      "learning_rate": 7.750582082977467e-05,
      "loss": 0.8454,
      "step": 171
    },
    {
      "epoch": 0.002286466312840436,
      "grad_norm": 0.8678277730941772,
      "learning_rate": 7.723195175075136e-05,
      "loss": 0.8347,
      "step": 172
    },
    {
      "epoch": 0.0022997597216360198,
      "grad_norm": 0.8320735692977905,
      "learning_rate": 7.695691614555003e-05,
      "loss": 0.7562,
      "step": 173
    },
    {
      "epoch": 0.0023130531304316037,
      "grad_norm": 0.8863369226455688,
      "learning_rate": 7.668072579578058e-05,
      "loss": 0.947,
      "step": 174
    },
    {
      "epoch": 0.0023263465392271876,
      "grad_norm": 0.8249924778938293,
      "learning_rate": 7.64033925325184e-05,
      "loss": 0.6974,
      "step": 175
    },
    {
      "epoch": 0.0023396399480227715,
      "grad_norm": 1.002340316772461,
      "learning_rate": 7.612492823579745e-05,
      "loss": 0.7797,
      "step": 176
    },
    {
      "epoch": 0.0023529333568183554,
      "grad_norm": 0.9412791728973389,
      "learning_rate": 7.584534483410137e-05,
      "loss": 0.8217,
      "step": 177
    },
    {
      "epoch": 0.0023662267656139394,
      "grad_norm": 0.8319302201271057,
      "learning_rate": 7.55646543038526e-05,
      "loss": 0.7363,
      "step": 178
    },
    {
      "epoch": 0.0023795201744095233,
      "grad_norm": 0.9082163572311401,
      "learning_rate": 7.528286866889924e-05,
      "loss": 0.7428,
      "step": 179
    },
    {
      "epoch": 0.002392813583205107,
      "grad_norm": 0.9351644515991211,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7053,
      "step": 180
    },
    {
      "epoch": 0.002406106992000691,
      "grad_norm": 1.027571439743042,
      "learning_rate": 7.471606041430723e-05,
      "loss": 0.8533,
      "step": 181
    },
    {
      "epoch": 0.002419400400796275,
      "grad_norm": 1.1358752250671387,
      "learning_rate": 7.443106207484776e-05,
      "loss": 0.9333,
      "step": 182
    },
    {
      "epoch": 0.002432693809591859,
      "grad_norm": 1.065809726715088,
      "learning_rate": 7.414501719000187e-05,
      "loss": 0.6901,
      "step": 183
    },
    {
      "epoch": 0.002445987218387443,
      "grad_norm": 1.0382061004638672,
      "learning_rate": 7.385793801298042e-05,
      "loss": 0.8267,
      "step": 184
    },
    {
      "epoch": 0.002459280627183027,
      "grad_norm": 1.1729737520217896,
      "learning_rate": 7.35698368412999e-05,
      "loss": 0.7518,
      "step": 185
    },
    {
      "epoch": 0.002472574035978611,
      "grad_norm": 1.0536710023880005,
      "learning_rate": 7.328072601625557e-05,
      "loss": 0.8129,
      "step": 186
    },
    {
      "epoch": 0.002485867444774195,
      "grad_norm": 1.2995885610580444,
      "learning_rate": 7.2990617922393e-05,
      "loss": 0.7496,
      "step": 187
    },
    {
      "epoch": 0.002499160853569779,
      "grad_norm": 1.3245257139205933,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.8155,
      "step": 188
    },
    {
      "epoch": 0.002512454262365363,
      "grad_norm": 1.360560417175293,
      "learning_rate": 7.240745967946113e-05,
      "loss": 0.8575,
      "step": 189
    },
    {
      "epoch": 0.0025257476711609468,
      "grad_norm": 1.4591000080108643,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.7878,
      "step": 190
    },
    {
      "epoch": 0.0025390410799565307,
      "grad_norm": 1.2115497589111328,
      "learning_rate": 7.18204620336671e-05,
      "loss": 0.6024,
      "step": 191
    },
    {
      "epoch": 0.0025523344887521146,
      "grad_norm": 1.2243151664733887,
      "learning_rate": 7.152555484041476e-05,
      "loss": 0.8045,
      "step": 192
    },
    {
      "epoch": 0.0025656278975476985,
      "grad_norm": 1.1854766607284546,
      "learning_rate": 7.122972556403567e-05,
      "loss": 0.7555,
      "step": 193
    },
    {
      "epoch": 0.0025789213063432824,
      "grad_norm": 1.4770948886871338,
      "learning_rate": 7.09329868768714e-05,
      "loss": 0.7578,
      "step": 194
    },
    {
      "epoch": 0.0025922147151388663,
      "grad_norm": 1.6484698057174683,
      "learning_rate": 7.063535149021973e-05,
      "loss": 0.7634,
      "step": 195
    },
    {
      "epoch": 0.0026055081239344502,
      "grad_norm": 1.3997423648834229,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.7521,
      "step": 196
    },
    {
      "epoch": 0.002618801532730034,
      "grad_norm": 1.3965321779251099,
      "learning_rate": 7.003744165515705e-05,
      "loss": 0.6411,
      "step": 197
    },
    {
      "epoch": 0.002632094941525618,
      "grad_norm": 1.8712222576141357,
      "learning_rate": 6.973719281921335e-05,
      "loss": 0.7567,
      "step": 198
    },
    {
      "epoch": 0.002645388350321202,
      "grad_norm": 1.475347876548767,
      "learning_rate": 6.943609850761979e-05,
      "loss": 0.7531,
      "step": 199
    },
    {
      "epoch": 0.002658681759116786,
      "grad_norm": 3.6233763694763184,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8044,
      "step": 200
    },
    {
      "epoch": 0.002658681759116786,
      "eval_loss": 0.8204836845397949,
      "eval_runtime": 5386.3531,
      "eval_samples_per_second": 23.522,
      "eval_steps_per_second": 5.88,
      "step": 200
    },
    {
      "epoch": 0.00267197516791237,
      "grad_norm": 0.45648401975631714,
      "learning_rate": 6.883142508466054e-05,
      "loss": 1.0279,
      "step": 201
    },
    {
      "epoch": 0.0026852685767079537,
      "grad_norm": 0.7271209359169006,
      "learning_rate": 6.852787187549182e-05,
      "loss": 0.829,
      "step": 202
    },
    {
      "epoch": 0.0026985619855035376,
      "grad_norm": 0.7703710198402405,
      "learning_rate": 6.82235249939575e-05,
      "loss": 0.9791,
      "step": 203
    },
    {
      "epoch": 0.0027118553942991216,
      "grad_norm": 0.6340277791023254,
      "learning_rate": 6.7918397477265e-05,
      "loss": 1.0537,
      "step": 204
    },
    {
      "epoch": 0.0027251488030947055,
      "grad_norm": 0.6891186237335205,
      "learning_rate": 6.761250239606169e-05,
      "loss": 0.7271,
      "step": 205
    },
    {
      "epoch": 0.0027384422118902894,
      "grad_norm": 0.6540559530258179,
      "learning_rate": 6.730585285387465e-05,
      "loss": 0.9029,
      "step": 206
    },
    {
      "epoch": 0.0027517356206858733,
      "grad_norm": 0.7297558188438416,
      "learning_rate": 6.699846198654971e-05,
      "loss": 0.7676,
      "step": 207
    },
    {
      "epoch": 0.0027650290294814572,
      "grad_norm": 0.7272955775260925,
      "learning_rate": 6.669034296168855e-05,
      "loss": 0.8868,
      "step": 208
    },
    {
      "epoch": 0.002778322438277041,
      "grad_norm": 0.6929868459701538,
      "learning_rate": 6.638150897808468e-05,
      "loss": 0.8485,
      "step": 209
    },
    {
      "epoch": 0.002791615847072625,
      "grad_norm": 0.6661206483840942,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.9857,
      "step": 210
    },
    {
      "epoch": 0.002804909255868209,
      "grad_norm": 0.788245439529419,
      "learning_rate": 6.57617490823885e-05,
      "loss": 1.0112,
      "step": 211
    },
    {
      "epoch": 0.002818202664663793,
      "grad_norm": 0.6952183246612549,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9415,
      "step": 212
    },
    {
      "epoch": 0.002831496073459377,
      "grad_norm": 0.7681757211685181,
      "learning_rate": 6.513928849212873e-05,
      "loss": 0.8243,
      "step": 213
    },
    {
      "epoch": 0.002844789482254961,
      "grad_norm": 0.6462027430534363,
      "learning_rate": 6.482707874877854e-05,
      "loss": 0.9504,
      "step": 214
    },
    {
      "epoch": 0.002858082891050545,
      "grad_norm": 0.9063102602958679,
      "learning_rate": 6.451423386272312e-05,
      "loss": 0.8883,
      "step": 215
    },
    {
      "epoch": 0.002871376299846129,
      "grad_norm": 0.6706687211990356,
      "learning_rate": 6.420076723519614e-05,
      "loss": 0.929,
      "step": 216
    },
    {
      "epoch": 0.002884669708641713,
      "grad_norm": 0.8108212947845459,
      "learning_rate": 6.388669229406462e-05,
      "loss": 0.8639,
      "step": 217
    },
    {
      "epoch": 0.002897963117437297,
      "grad_norm": 0.8935511112213135,
      "learning_rate": 6.357202249325371e-05,
      "loss": 0.7643,
      "step": 218
    },
    {
      "epoch": 0.0029112565262328807,
      "grad_norm": 0.733965277671814,
      "learning_rate": 6.32567713121704e-05,
      "loss": 0.7395,
      "step": 219
    },
    {
      "epoch": 0.0029245499350284646,
      "grad_norm": 0.817078173160553,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8897,
      "step": 220
    },
    {
      "epoch": 0.0029378433438240485,
      "grad_norm": 0.7985368371009827,
      "learning_rate": 6.26245788507579e-05,
      "loss": 0.8386,
      "step": 221
    },
    {
      "epoch": 0.0029511367526196325,
      "grad_norm": 1.066880226135254,
      "learning_rate": 6.230766465144967e-05,
      "loss": 0.865,
      "step": 222
    },
    {
      "epoch": 0.0029644301614152164,
      "grad_norm": 0.9088742733001709,
      "learning_rate": 6.199022323275083e-05,
      "loss": 0.8156,
      "step": 223
    },
    {
      "epoch": 0.0029777235702108003,
      "grad_norm": 0.858835756778717,
      "learning_rate": 6.167226819279528e-05,
      "loss": 0.8327,
      "step": 224
    },
    {
      "epoch": 0.002991016979006384,
      "grad_norm": 0.877459704875946,
      "learning_rate": 6.135381315171867e-05,
      "loss": 0.7427,
      "step": 225
    },
    {
      "epoch": 0.003004310387801968,
      "grad_norm": 0.9818418025970459,
      "learning_rate": 6.103487175107507e-05,
      "loss": 0.7461,
      "step": 226
    },
    {
      "epoch": 0.003017603796597552,
      "grad_norm": 0.865171492099762,
      "learning_rate": 6.071545765325254e-05,
      "loss": 0.8451,
      "step": 227
    },
    {
      "epoch": 0.003030897205393136,
      "grad_norm": 0.9747686982154846,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.8161,
      "step": 228
    },
    {
      "epoch": 0.00304419061418872,
      "grad_norm": 0.9070019125938416,
      "learning_rate": 6.007526611628086e-05,
      "loss": 0.7587,
      "step": 229
    },
    {
      "epoch": 0.0030574840229843038,
      "grad_norm": 1.0461353063583374,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.807,
      "step": 230
    },
    {
      "epoch": 0.0030707774317798877,
      "grad_norm": 0.926591157913208,
      "learning_rate": 5.9433348234327765e-05,
      "loss": 0.7647,
      "step": 231
    },
    {
      "epoch": 0.0030840708405754716,
      "grad_norm": 1.024192452430725,
      "learning_rate": 5.911177627460739e-05,
      "loss": 0.8465,
      "step": 232
    },
    {
      "epoch": 0.0030973642493710555,
      "grad_norm": 1.1028368473052979,
      "learning_rate": 5.8789813996717736e-05,
      "loss": 0.8377,
      "step": 233
    },
    {
      "epoch": 0.0031106576581666394,
      "grad_norm": 0.9542917609214783,
      "learning_rate": 5.8467475192451226e-05,
      "loss": 0.8081,
      "step": 234
    },
    {
      "epoch": 0.0031239510669622233,
      "grad_norm": 1.0834472179412842,
      "learning_rate": 5.814477366972945e-05,
      "loss": 0.7806,
      "step": 235
    },
    {
      "epoch": 0.0031372444757578073,
      "grad_norm": 1.5537927150726318,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.9589,
      "step": 236
    },
    {
      "epoch": 0.003150537884553391,
      "grad_norm": 1.0712422132492065,
      "learning_rate": 5.749833777770225e-05,
      "loss": 0.7476,
      "step": 237
    },
    {
      "epoch": 0.003163831293348975,
      "grad_norm": 1.0612425804138184,
      "learning_rate": 5.717463109955896e-05,
      "loss": 0.8508,
      "step": 238
    },
    {
      "epoch": 0.003177124702144559,
      "grad_norm": 1.092305064201355,
      "learning_rate": 5.685061708409841e-05,
      "loss": 0.7743,
      "step": 239
    },
    {
      "epoch": 0.003190418110940143,
      "grad_norm": 1.3009710311889648,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.8238,
      "step": 240
    },
    {
      "epoch": 0.003203711519735727,
      "grad_norm": 1.1749954223632812,
      "learning_rate": 5.6201722572524275e-05,
      "loss": 0.6972,
      "step": 241
    },
    {
      "epoch": 0.003217004928531311,
      "grad_norm": 1.3417279720306396,
      "learning_rate": 5.587686987289189e-05,
      "loss": 0.6686,
      "step": 242
    },
    {
      "epoch": 0.003230298337326895,
      "grad_norm": 1.2631011009216309,
      "learning_rate": 5.5551765427713884e-05,
      "loss": 0.5261,
      "step": 243
    },
    {
      "epoch": 0.003243591746122479,
      "grad_norm": 1.4057419300079346,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.7018,
      "step": 244
    },
    {
      "epoch": 0.003256885154918063,
      "grad_norm": 1.2598075866699219,
      "learning_rate": 5.490085701647805e-05,
      "loss": 0.6326,
      "step": 245
    },
    {
      "epoch": 0.003270178563713647,
      "grad_norm": 1.4153088331222534,
      "learning_rate": 5.457508093317013e-05,
      "loss": 0.7415,
      "step": 246
    },
    {
      "epoch": 0.0032834719725092307,
      "grad_norm": 1.358693242073059,
      "learning_rate": 5.4249108868622086e-05,
      "loss": 0.6439,
      "step": 247
    },
    {
      "epoch": 0.0032967653813048147,
      "grad_norm": 1.7730319499969482,
      "learning_rate": 5.392295478639225e-05,
      "loss": 0.68,
      "step": 248
    },
    {
      "epoch": 0.0033100587901003986,
      "grad_norm": 1.7520637512207031,
      "learning_rate": 5.359663265783598e-05,
      "loss": 0.7038,
      "step": 249
    },
    {
      "epoch": 0.0033233521988959825,
      "grad_norm": 2.459104061126709,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.7434,
      "step": 250
    },
    {
      "epoch": 0.0033366456076915664,
      "grad_norm": 0.40572744607925415,
      "learning_rate": 5.294354018255945e-05,
      "loss": 0.865,
      "step": 251
    },
    {
      "epoch": 0.0033499390164871503,
      "grad_norm": 0.561611533164978,
      "learning_rate": 5.26167978121472e-05,
      "loss": 0.7732,
      "step": 252
    },
    {
      "epoch": 0.0033632324252827342,
      "grad_norm": 0.766336977481842,
      "learning_rate": 5.228994334682604e-05,
      "loss": 0.9102,
      "step": 253
    },
    {
      "epoch": 0.003376525834078318,
      "grad_norm": 0.6782603859901428,
      "learning_rate": 5.196299078795344e-05,
      "loss": 0.76,
      "step": 254
    },
    {
      "epoch": 0.003389819242873902,
      "grad_norm": 0.6662617921829224,
      "learning_rate": 5.1635954141088813e-05,
      "loss": 0.9271,
      "step": 255
    },
    {
      "epoch": 0.003403112651669486,
      "grad_norm": 0.6110439300537109,
      "learning_rate": 5.1308847415393666e-05,
      "loss": 0.767,
      "step": 256
    },
    {
      "epoch": 0.00341640606046507,
      "grad_norm": 0.7743271589279175,
      "learning_rate": 5.0981684623031415e-05,
      "loss": 0.8052,
      "step": 257
    },
    {
      "epoch": 0.003429699469260654,
      "grad_norm": 0.6447152495384216,
      "learning_rate": 5.0654479778567223e-05,
      "loss": 0.8057,
      "step": 258
    },
    {
      "epoch": 0.0034429928780562377,
      "grad_norm": 0.7686765789985657,
      "learning_rate": 5.0327246898367597e-05,
      "loss": 1.0002,
      "step": 259
    },
    {
      "epoch": 0.0034562862868518216,
      "grad_norm": 0.7462400794029236,
      "learning_rate": 5e-05,
      "loss": 0.9923,
      "step": 260
    },
    {
      "epoch": 0.0034695796956474055,
      "grad_norm": 0.6527460813522339,
      "learning_rate": 4.9672753101632415e-05,
      "loss": 0.9351,
      "step": 261
    },
    {
      "epoch": 0.0034828731044429895,
      "grad_norm": 0.8053703308105469,
      "learning_rate": 4.934552022143279e-05,
      "loss": 0.8587,
      "step": 262
    },
    {
      "epoch": 0.0034961665132385734,
      "grad_norm": 0.6980494856834412,
      "learning_rate": 4.901831537696859e-05,
      "loss": 0.8553,
      "step": 263
    },
    {
      "epoch": 0.0035094599220341573,
      "grad_norm": 0.7816311717033386,
      "learning_rate": 4.869115258460635e-05,
      "loss": 0.8387,
      "step": 264
    },
    {
      "epoch": 0.003522753330829741,
      "grad_norm": 0.7028314471244812,
      "learning_rate": 4.83640458589112e-05,
      "loss": 0.779,
      "step": 265
    },
    {
      "epoch": 0.003536046739625325,
      "grad_norm": 0.673923909664154,
      "learning_rate": 4.8037009212046586e-05,
      "loss": 0.9134,
      "step": 266
    },
    {
      "epoch": 0.003549340148420909,
      "grad_norm": 0.8537097573280334,
      "learning_rate": 4.7710056653173976e-05,
      "loss": 0.8188,
      "step": 267
    },
    {
      "epoch": 0.003562633557216493,
      "grad_norm": 0.9176320433616638,
      "learning_rate": 4.738320218785281e-05,
      "loss": 0.8542,
      "step": 268
    },
    {
      "epoch": 0.003575926966012077,
      "grad_norm": 0.7979686856269836,
      "learning_rate": 4.7056459817440544e-05,
      "loss": 0.8573,
      "step": 269
    },
    {
      "epoch": 0.003589220374807661,
      "grad_norm": 0.895863950252533,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.8856,
      "step": 270
    },
    {
      "epoch": 0.003602513783603245,
      "grad_norm": 0.7678753137588501,
      "learning_rate": 4.640336734216403e-05,
      "loss": 0.825,
      "step": 271
    },
    {
      "epoch": 0.003615807192398829,
      "grad_norm": 0.7857531905174255,
      "learning_rate": 4.607704521360776e-05,
      "loss": 0.8264,
      "step": 272
    },
    {
      "epoch": 0.003629100601194413,
      "grad_norm": 0.8283319473266602,
      "learning_rate": 4.575089113137792e-05,
      "loss": 0.9319,
      "step": 273
    },
    {
      "epoch": 0.003642394009989997,
      "grad_norm": 0.907440721988678,
      "learning_rate": 4.542491906682989e-05,
      "loss": 0.9424,
      "step": 274
    },
    {
      "epoch": 0.0036556874187855808,
      "grad_norm": 0.767007052898407,
      "learning_rate": 4.509914298352197e-05,
      "loss": 0.7332,
      "step": 275
    },
    {
      "epoch": 0.0036689808275811647,
      "grad_norm": 0.858820378780365,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.6919,
      "step": 276
    },
    {
      "epoch": 0.0036822742363767486,
      "grad_norm": 0.9303252696990967,
      "learning_rate": 4.444823457228612e-05,
      "loss": 0.8451,
      "step": 277
    },
    {
      "epoch": 0.0036955676451723325,
      "grad_norm": 0.9113172292709351,
      "learning_rate": 4.412313012710813e-05,
      "loss": 0.7171,
      "step": 278
    },
    {
      "epoch": 0.0037088610539679164,
      "grad_norm": 0.8863866329193115,
      "learning_rate": 4.379827742747575e-05,
      "loss": 0.7568,
      "step": 279
    },
    {
      "epoch": 0.0037221544627635004,
      "grad_norm": 1.0519394874572754,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.859,
      "step": 280
    },
    {
      "epoch": 0.0037354478715590843,
      "grad_norm": 0.9415047764778137,
      "learning_rate": 4.3149382915901606e-05,
      "loss": 0.7797,
      "step": 281
    },
    {
      "epoch": 0.003748741280354668,
      "grad_norm": 0.9097842574119568,
      "learning_rate": 4.282536890044104e-05,
      "loss": 0.7683,
      "step": 282
    },
    {
      "epoch": 0.003762034689150252,
      "grad_norm": 0.930111825466156,
      "learning_rate": 4.250166222229774e-05,
      "loss": 0.8165,
      "step": 283
    },
    {
      "epoch": 0.003775328097945836,
      "grad_norm": 0.9701312184333801,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.8204,
      "step": 284
    },
    {
      "epoch": 0.00378862150674142,
      "grad_norm": 0.9940425753593445,
      "learning_rate": 4.185522633027057e-05,
      "loss": 0.7556,
      "step": 285
    },
    {
      "epoch": 0.003801914915537004,
      "grad_norm": 1.4344955682754517,
      "learning_rate": 4.153252480754877e-05,
      "loss": 0.8166,
      "step": 286
    },
    {
      "epoch": 0.0038152083243325878,
      "grad_norm": 1.0159411430358887,
      "learning_rate": 4.1210186003282275e-05,
      "loss": 0.741,
      "step": 287
    },
    {
      "epoch": 0.0038285017331281717,
      "grad_norm": 1.2148553133010864,
      "learning_rate": 4.088822372539263e-05,
      "loss": 0.7717,
      "step": 288
    },
    {
      "epoch": 0.0038417951419237556,
      "grad_norm": 1.135869026184082,
      "learning_rate": 4.0566651765672246e-05,
      "loss": 0.7963,
      "step": 289
    },
    {
      "epoch": 0.0038550885507193395,
      "grad_norm": 1.098055362701416,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.7539,
      "step": 290
    },
    {
      "epoch": 0.0038683819595149234,
      "grad_norm": 1.2564170360565186,
      "learning_rate": 3.992473388371915e-05,
      "loss": 0.9587,
      "step": 291
    },
    {
      "epoch": 0.0038816753683105073,
      "grad_norm": 1.2259382009506226,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.7717,
      "step": 292
    },
    {
      "epoch": 0.0038949687771060912,
      "grad_norm": 1.2078173160552979,
      "learning_rate": 3.928454234674747e-05,
      "loss": 0.7425,
      "step": 293
    },
    {
      "epoch": 0.003908262185901675,
      "grad_norm": 1.328354001045227,
      "learning_rate": 3.896512824892495e-05,
      "loss": 0.6838,
      "step": 294
    },
    {
      "epoch": 0.0039215555946972595,
      "grad_norm": 1.3222585916519165,
      "learning_rate": 3.864618684828134e-05,
      "loss": 0.6053,
      "step": 295
    },
    {
      "epoch": 0.003934849003492843,
      "grad_norm": 1.7178049087524414,
      "learning_rate": 3.832773180720475e-05,
      "loss": 0.6933,
      "step": 296
    },
    {
      "epoch": 0.003948142412288427,
      "grad_norm": 1.406863808631897,
      "learning_rate": 3.800977676724919e-05,
      "loss": 0.6524,
      "step": 297
    },
    {
      "epoch": 0.003961435821084011,
      "grad_norm": 1.4337832927703857,
      "learning_rate": 3.769233534855035e-05,
      "loss": 0.5845,
      "step": 298
    },
    {
      "epoch": 0.003974729229879595,
      "grad_norm": 1.893900990486145,
      "learning_rate": 3.73754211492421e-05,
      "loss": 0.7638,
      "step": 299
    },
    {
      "epoch": 0.003988022638675179,
      "grad_norm": 2.386813163757324,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.9554,
      "step": 300
    },
    {
      "epoch": 0.003988022638675179,
      "eval_loss": 0.7951595783233643,
      "eval_runtime": 5382.5665,
      "eval_samples_per_second": 23.538,
      "eval_steps_per_second": 5.885,
      "step": 300
    },
    {
      "epoch": 0.004001316047470763,
      "grad_norm": 0.3682875633239746,
      "learning_rate": 3.6743228687829595e-05,
      "loss": 0.9057,
      "step": 301
    },
    {
      "epoch": 0.0040146094562663465,
      "grad_norm": 0.6787735819816589,
      "learning_rate": 3.642797750674629e-05,
      "loss": 0.9395,
      "step": 302
    },
    {
      "epoch": 0.004027902865061931,
      "grad_norm": 0.6592588424682617,
      "learning_rate": 3.6113307705935396e-05,
      "loss": 1.02,
      "step": 303
    },
    {
      "epoch": 0.004041196273857514,
      "grad_norm": 0.5961223840713501,
      "learning_rate": 3.579923276480387e-05,
      "loss": 0.8226,
      "step": 304
    },
    {
      "epoch": 0.004054489682653099,
      "grad_norm": 0.7095391750335693,
      "learning_rate": 3.5485766137276894e-05,
      "loss": 0.7234,
      "step": 305
    },
    {
      "epoch": 0.004067783091448682,
      "grad_norm": 0.5839325785636902,
      "learning_rate": 3.5172921251221455e-05,
      "loss": 0.9561,
      "step": 306
    },
    {
      "epoch": 0.0040810765002442665,
      "grad_norm": 0.8775228261947632,
      "learning_rate": 3.486071150787128e-05,
      "loss": 0.8771,
      "step": 307
    },
    {
      "epoch": 0.00409436990903985,
      "grad_norm": 0.7337412238121033,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.0445,
      "step": 308
    },
    {
      "epoch": 0.004107663317835434,
      "grad_norm": 0.9464497566223145,
      "learning_rate": 3.423825091761153e-05,
      "loss": 0.8443,
      "step": 309
    },
    {
      "epoch": 0.004120956726631018,
      "grad_norm": 0.709404706954956,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.7649,
      "step": 310
    },
    {
      "epoch": 0.004134250135426602,
      "grad_norm": 0.6507409811019897,
      "learning_rate": 3.361849102191533e-05,
      "loss": 0.9584,
      "step": 311
    },
    {
      "epoch": 0.004147543544222186,
      "grad_norm": 0.7024583220481873,
      "learning_rate": 3.330965703831146e-05,
      "loss": 0.861,
      "step": 312
    },
    {
      "epoch": 0.00416083695301777,
      "grad_norm": 0.7223301529884338,
      "learning_rate": 3.300153801345028e-05,
      "loss": 0.8675,
      "step": 313
    },
    {
      "epoch": 0.004174130361813354,
      "grad_norm": 0.8610208034515381,
      "learning_rate": 3.2694147146125345e-05,
      "loss": 0.8974,
      "step": 314
    },
    {
      "epoch": 0.004187423770608938,
      "grad_norm": 0.7962211966514587,
      "learning_rate": 3.2387497603938326e-05,
      "loss": 0.9931,
      "step": 315
    },
    {
      "epoch": 0.004200717179404522,
      "grad_norm": 0.640409529209137,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.8171,
      "step": 316
    },
    {
      "epoch": 0.004214010588200106,
      "grad_norm": 0.6672929525375366,
      "learning_rate": 3.177647500604252e-05,
      "loss": 0.9031,
      "step": 317
    },
    {
      "epoch": 0.00422730399699569,
      "grad_norm": 0.8444193601608276,
      "learning_rate": 3.147212812450819e-05,
      "loss": 0.7829,
      "step": 318
    },
    {
      "epoch": 0.0042405974057912734,
      "grad_norm": 0.9428850412368774,
      "learning_rate": 3.116857491533947e-05,
      "loss": 0.9054,
      "step": 319
    },
    {
      "epoch": 0.004253890814586858,
      "grad_norm": 0.8064233660697937,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.8479,
      "step": 320
    },
    {
      "epoch": 0.004267184223382441,
      "grad_norm": 0.7298509478569031,
      "learning_rate": 3.056390149238022e-05,
      "loss": 0.8549,
      "step": 321
    },
    {
      "epoch": 0.004280477632178026,
      "grad_norm": 0.8034161925315857,
      "learning_rate": 3.0262807180786647e-05,
      "loss": 0.7365,
      "step": 322
    },
    {
      "epoch": 0.004293771040973609,
      "grad_norm": 0.9719378352165222,
      "learning_rate": 2.996255834484296e-05,
      "loss": 0.7941,
      "step": 323
    },
    {
      "epoch": 0.0043070644497691934,
      "grad_norm": 0.8183806538581848,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.7686,
      "step": 324
    },
    {
      "epoch": 0.004320357858564777,
      "grad_norm": 0.8338200449943542,
      "learning_rate": 2.936464850978027e-05,
      "loss": 0.7358,
      "step": 325
    },
    {
      "epoch": 0.004333651267360361,
      "grad_norm": 0.8162009716033936,
      "learning_rate": 2.9067013123128613e-05,
      "loss": 0.7198,
      "step": 326
    },
    {
      "epoch": 0.004346944676155945,
      "grad_norm": 0.8127380609512329,
      "learning_rate": 2.8770274435964355e-05,
      "loss": 0.8007,
      "step": 327
    },
    {
      "epoch": 0.004360238084951529,
      "grad_norm": 1.0705251693725586,
      "learning_rate": 2.8474445159585235e-05,
      "loss": 0.6692,
      "step": 328
    },
    {
      "epoch": 0.004373531493747113,
      "grad_norm": 0.9033278226852417,
      "learning_rate": 2.8179537966332887e-05,
      "loss": 0.8257,
      "step": 329
    },
    {
      "epoch": 0.004386824902542697,
      "grad_norm": 0.8514038920402527,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.6896,
      "step": 330
    },
    {
      "epoch": 0.00440011831133828,
      "grad_norm": 1.007850170135498,
      "learning_rate": 2.759254032053888e-05,
      "loss": 0.7821,
      "step": 331
    },
    {
      "epoch": 0.004413411720133865,
      "grad_norm": 0.9796565175056458,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.8207,
      "step": 332
    },
    {
      "epoch": 0.004426705128929448,
      "grad_norm": 0.9511303305625916,
      "learning_rate": 2.700938207760701e-05,
      "loss": 0.7905,
      "step": 333
    },
    {
      "epoch": 0.004439998537725033,
      "grad_norm": 1.1630312204360962,
      "learning_rate": 2.671927398374443e-05,
      "loss": 0.8584,
      "step": 334
    },
    {
      "epoch": 0.004453291946520616,
      "grad_norm": 0.9065108299255371,
      "learning_rate": 2.6430163158700115e-05,
      "loss": 0.9217,
      "step": 335
    },
    {
      "epoch": 0.0044665853553162,
      "grad_norm": 1.055619716644287,
      "learning_rate": 2.6142061987019577e-05,
      "loss": 0.6102,
      "step": 336
    },
    {
      "epoch": 0.004479878764111784,
      "grad_norm": 1.02480947971344,
      "learning_rate": 2.5854982809998153e-05,
      "loss": 0.7305,
      "step": 337
    },
    {
      "epoch": 0.004493172172907368,
      "grad_norm": 0.9915962219238281,
      "learning_rate": 2.556893792515227e-05,
      "loss": 0.7496,
      "step": 338
    },
    {
      "epoch": 0.004506465581702952,
      "grad_norm": 1.1916135549545288,
      "learning_rate": 2.5283939585692783e-05,
      "loss": 0.7384,
      "step": 339
    },
    {
      "epoch": 0.004519758990498536,
      "grad_norm": 1.0934064388275146,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7266,
      "step": 340
    },
    {
      "epoch": 0.00453305239929412,
      "grad_norm": 1.1802442073822021,
      "learning_rate": 2.471713133110078e-05,
      "loss": 0.8202,
      "step": 341
    },
    {
      "epoch": 0.004546345808089704,
      "grad_norm": 1.246431827545166,
      "learning_rate": 2.4435345696147403e-05,
      "loss": 0.6611,
      "step": 342
    },
    {
      "epoch": 0.004559639216885288,
      "grad_norm": 1.2618402242660522,
      "learning_rate": 2.4154655165898627e-05,
      "loss": 0.8292,
      "step": 343
    },
    {
      "epoch": 0.004572932625680872,
      "grad_norm": 1.327660083770752,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 0.6573,
      "step": 344
    },
    {
      "epoch": 0.004586226034476456,
      "grad_norm": 1.423105239868164,
      "learning_rate": 2.3596607467481603e-05,
      "loss": 0.8607,
      "step": 345
    },
    {
      "epoch": 0.0045995194432720396,
      "grad_norm": 1.4211772680282593,
      "learning_rate": 2.3319274204219428e-05,
      "loss": 0.8172,
      "step": 346
    },
    {
      "epoch": 0.004612812852067624,
      "grad_norm": 1.8413368463516235,
      "learning_rate": 2.3043083854449988e-05,
      "loss": 0.8123,
      "step": 347
    },
    {
      "epoch": 0.004626106260863207,
      "grad_norm": 1.8232938051223755,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 1.0117,
      "step": 348
    },
    {
      "epoch": 0.004639399669658792,
      "grad_norm": 1.8290114402770996,
      "learning_rate": 2.2494179170225333e-05,
      "loss": 0.5543,
      "step": 349
    },
    {
      "epoch": 0.004652693078454375,
      "grad_norm": 2.2341887950897217,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.8504,
      "step": 350
    },
    {
      "epoch": 0.00466598648724996,
      "grad_norm": 0.398695707321167,
      "learning_rate": 2.194998746679952e-05,
      "loss": 0.9286,
      "step": 351
    },
    {
      "epoch": 0.004679279896045543,
      "grad_norm": 0.4740478992462158,
      "learning_rate": 2.167968815375837e-05,
      "loss": 0.9106,
      "step": 352
    },
    {
      "epoch": 0.004692573304841127,
      "grad_norm": 0.5932014584541321,
      "learning_rate": 2.1410601988619394e-05,
      "loss": 1.0187,
      "step": 353
    },
    {
      "epoch": 0.004705866713636711,
      "grad_norm": 0.5926346182823181,
      "learning_rate": 2.1142740498138324e-05,
      "loss": 0.8136,
      "step": 354
    },
    {
      "epoch": 0.004719160122432295,
      "grad_norm": 0.6267058849334717,
      "learning_rate": 2.08761151566099e-05,
      "loss": 0.8732,
      "step": 355
    },
    {
      "epoch": 0.004732453531227879,
      "grad_norm": 0.7424627542495728,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8189,
      "step": 356
    },
    {
      "epoch": 0.004745746940023463,
      "grad_norm": 0.6441757082939148,
      "learning_rate": 2.034661855233815e-05,
      "loss": 0.9271,
      "step": 357
    },
    {
      "epoch": 0.0047590403488190465,
      "grad_norm": 0.6926533579826355,
      "learning_rate": 2.008376997146705e-05,
      "loss": 0.9045,
      "step": 358
    },
    {
      "epoch": 0.004772333757614631,
      "grad_norm": 0.6195574402809143,
      "learning_rate": 1.982220290232143e-05,
      "loss": 1.0152,
      "step": 359
    },
    {
      "epoch": 0.004785627166410214,
      "grad_norm": 0.6188430190086365,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.8955,
      "step": 360
    },
    {
      "epoch": 0.004798920575205799,
      "grad_norm": 0.7343001365661621,
      "learning_rate": 1.9302958062481673e-05,
      "loss": 0.7987,
      "step": 361
    },
    {
      "epoch": 0.004812213984001382,
      "grad_norm": 0.7568181157112122,
      "learning_rate": 1.9045302534508297e-05,
      "loss": 0.7997,
      "step": 362
    },
    {
      "epoch": 0.0048255073927969665,
      "grad_norm": 0.6235895752906799,
      "learning_rate": 1.8788973002749112e-05,
      "loss": 0.7439,
      "step": 363
    },
    {
      "epoch": 0.00483880080159255,
      "grad_norm": 0.7460948824882507,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 0.7819,
      "step": 364
    },
    {
      "epoch": 0.004852094210388134,
      "grad_norm": 0.7286429405212402,
      "learning_rate": 1.8280335791817733e-05,
      "loss": 0.8258,
      "step": 365
    },
    {
      "epoch": 0.004865387619183718,
      "grad_norm": 0.7679296731948853,
      "learning_rate": 1.8028049900970767e-05,
      "loss": 0.8291,
      "step": 366
    },
    {
      "epoch": 0.004878681027979302,
      "grad_norm": 0.7549829483032227,
      "learning_rate": 1.777713358205514e-05,
      "loss": 0.7981,
      "step": 367
    },
    {
      "epoch": 0.004891974436774886,
      "grad_norm": 0.7160136103630066,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 0.836,
      "step": 368
    },
    {
      "epoch": 0.00490526784557047,
      "grad_norm": 0.8430051207542419,
      "learning_rate": 1.7279452594569483e-05,
      "loss": 0.7635,
      "step": 369
    },
    {
      "epoch": 0.004918561254366054,
      "grad_norm": 0.8327125906944275,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.7745,
      "step": 370
    },
    {
      "epoch": 0.004931854663161638,
      "grad_norm": 0.7590059638023376,
      "learning_rate": 1.678737810443593e-05,
      "loss": 0.8438,
      "step": 371
    },
    {
      "epoch": 0.004945148071957222,
      "grad_norm": 0.7954879403114319,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.8612,
      "step": 372
    },
    {
      "epoch": 0.004958441480752806,
      "grad_norm": 0.7659891247749329,
      "learning_rate": 1.6300994426085103e-05,
      "loss": 0.7596,
      "step": 373
    },
    {
      "epoch": 0.00497173488954839,
      "grad_norm": 0.8235825300216675,
      "learning_rate": 1.605996272335291e-05,
      "loss": 0.8399,
      "step": 374
    },
    {
      "epoch": 0.0049850282983439735,
      "grad_norm": 0.8220838308334351,
      "learning_rate": 1.5820384898856434e-05,
      "loss": 0.8225,
      "step": 375
    },
    {
      "epoch": 0.004998321707139558,
      "grad_norm": 0.826115608215332,
      "learning_rate": 1.5582271215312294e-05,
      "loss": 0.6883,
      "step": 376
    },
    {
      "epoch": 0.005011615115935141,
      "grad_norm": 0.9258382320404053,
      "learning_rate": 1.5345631872718214e-05,
      "loss": 0.7759,
      "step": 377
    },
    {
      "epoch": 0.005024908524730726,
      "grad_norm": 0.9057872891426086,
      "learning_rate": 1.5110477007916001e-05,
      "loss": 0.8996,
      "step": 378
    },
    {
      "epoch": 0.005038201933526309,
      "grad_norm": 0.8790716528892517,
      "learning_rate": 1.4876816694157419e-05,
      "loss": 0.8599,
      "step": 379
    },
    {
      "epoch": 0.0050514953423218935,
      "grad_norm": 0.8845470547676086,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7995,
      "step": 380
    },
    {
      "epoch": 0.005064788751117477,
      "grad_norm": 0.8347725868225098,
      "learning_rate": 1.4414019692241437e-05,
      "loss": 0.7993,
      "step": 381
    },
    {
      "epoch": 0.005078082159913061,
      "grad_norm": 0.8920494318008423,
      "learning_rate": 1.4184902828767287e-05,
      "loss": 0.644,
      "step": 382
    },
    {
      "epoch": 0.005091375568708645,
      "grad_norm": 0.9104064702987671,
      "learning_rate": 1.3957320164854059e-05,
      "loss": 0.8505,
      "step": 383
    },
    {
      "epoch": 0.005104668977504229,
      "grad_norm": 1.0407222509384155,
      "learning_rate": 1.373128144938563e-05,
      "loss": 0.7034,
      "step": 384
    },
    {
      "epoch": 0.005117962386299813,
      "grad_norm": 1.2223615646362305,
      "learning_rate": 1.3506796365108232e-05,
      "loss": 0.8768,
      "step": 385
    },
    {
      "epoch": 0.005131255795095397,
      "grad_norm": 0.9847481846809387,
      "learning_rate": 1.3283874528215733e-05,
      "loss": 0.6489,
      "step": 386
    },
    {
      "epoch": 0.0051445492038909805,
      "grad_norm": 0.9142990112304688,
      "learning_rate": 1.3062525487937699e-05,
      "loss": 0.7449,
      "step": 387
    },
    {
      "epoch": 0.005157842612686565,
      "grad_norm": 0.9533128142356873,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.7082,
      "step": 388
    },
    {
      "epoch": 0.005171136021482148,
      "grad_norm": 1.0442817211151123,
      "learning_rate": 1.2624583656870154e-05,
      "loss": 0.7579,
      "step": 389
    },
    {
      "epoch": 0.005184429430277733,
      "grad_norm": 1.190877079963684,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.6872,
      "step": 390
    },
    {
      "epoch": 0.005197722839073316,
      "grad_norm": 1.0062334537506104,
      "learning_rate": 1.2193045910983863e-05,
      "loss": 0.7513,
      "step": 391
    },
    {
      "epoch": 0.0052110162478689005,
      "grad_norm": 1.1777302026748657,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 0.6976,
      "step": 392
    },
    {
      "epoch": 0.005224309656664484,
      "grad_norm": 1.0158731937408447,
      "learning_rate": 1.1767986192049984e-05,
      "loss": 0.5948,
      "step": 393
    },
    {
      "epoch": 0.005237603065460068,
      "grad_norm": 1.2527599334716797,
      "learning_rate": 1.1557908396327028e-05,
      "loss": 0.7795,
      "step": 394
    },
    {
      "epoch": 0.005250896474255652,
      "grad_norm": 1.3996037244796753,
      "learning_rate": 1.134947733186315e-05,
      "loss": 0.7034,
      "step": 395
    },
    {
      "epoch": 0.005264189883051236,
      "grad_norm": 1.351304531097412,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 0.7591,
      "step": 396
    },
    {
      "epoch": 0.00527748329184682,
      "grad_norm": 1.4472730159759521,
      "learning_rate": 1.0937591039762085e-05,
      "loss": 0.5823,
      "step": 397
    },
    {
      "epoch": 0.005290776700642404,
      "grad_norm": 1.457184076309204,
      "learning_rate": 1.0734153455962765e-05,
      "loss": 0.7605,
      "step": 398
    },
    {
      "epoch": 0.005304070109437988,
      "grad_norm": 1.8055424690246582,
      "learning_rate": 1.0532397890342505e-05,
      "loss": 0.8625,
      "step": 399
    },
    {
      "epoch": 0.005317363518233572,
      "grad_norm": 3.0991199016571045,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.6841,
      "step": 400
    },
    {
      "epoch": 0.005317363518233572,
      "eval_loss": 0.7755893468856812,
      "eval_runtime": 5386.1571,
      "eval_samples_per_second": 23.523,
      "eval_steps_per_second": 5.881,
      "step": 400
    },
    {
      "epoch": 0.005330656927029156,
      "grad_norm": 0.40012648701667786,
      "learning_rate": 1.013396731136465e-05,
      "loss": 0.9604,
      "step": 401
    },
    {
      "epoch": 0.00534395033582474,
      "grad_norm": 0.5858917832374573,
      "learning_rate": 9.937309365446973e-06,
      "loss": 0.8581,
      "step": 402
    },
    {
      "epoch": 0.005357243744620324,
      "grad_norm": 0.5397459864616394,
      "learning_rate": 9.742367571857091e-06,
      "loss": 0.7486,
      "step": 403
    },
    {
      "epoch": 0.0053705371534159075,
      "grad_norm": 0.5918818116188049,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6034,
      "step": 404
    },
    {
      "epoch": 0.005383830562211492,
      "grad_norm": 0.6741821765899658,
      "learning_rate": 9.357665770419244e-06,
      "loss": 0.7264,
      "step": 405
    },
    {
      "epoch": 0.005397123971007075,
      "grad_norm": 0.6818976402282715,
      "learning_rate": 9.167922241916055e-06,
      "loss": 0.7604,
      "step": 406
    },
    {
      "epoch": 0.00541041737980266,
      "grad_norm": 0.5880439281463623,
      "learning_rate": 8.97992782372432e-06,
      "loss": 0.8363,
      "step": 407
    },
    {
      "epoch": 0.005423710788598243,
      "grad_norm": 0.5962891578674316,
      "learning_rate": 8.793690568899216e-06,
      "loss": 0.8284,
      "step": 408
    },
    {
      "epoch": 0.0054370041973938275,
      "grad_norm": 0.6675729751586914,
      "learning_rate": 8.609218455224893e-06,
      "loss": 0.8829,
      "step": 409
    },
    {
      "epoch": 0.005450297606189411,
      "grad_norm": 0.6426963210105896,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.8203,
      "step": 410
    },
    {
      "epoch": 0.005463591014984995,
      "grad_norm": 0.6224886178970337,
      "learning_rate": 8.245601184062852e-06,
      "loss": 0.8401,
      "step": 411
    },
    {
      "epoch": 0.005476884423780579,
      "grad_norm": 0.7933815717697144,
      "learning_rate": 8.066471602728803e-06,
      "loss": 0.9562,
      "step": 412
    },
    {
      "epoch": 0.005490177832576163,
      "grad_norm": 0.6306743621826172,
      "learning_rate": 7.889138314185678e-06,
      "loss": 0.8244,
      "step": 413
    },
    {
      "epoch": 0.005503471241371747,
      "grad_norm": 0.6678284406661987,
      "learning_rate": 7.71360891480134e-06,
      "loss": 0.9218,
      "step": 414
    },
    {
      "epoch": 0.005516764650167331,
      "grad_norm": 0.7518947720527649,
      "learning_rate": 7.539890923671062e-06,
      "loss": 0.8463,
      "step": 415
    },
    {
      "epoch": 0.0055300580589629144,
      "grad_norm": 0.7990968227386475,
      "learning_rate": 7.367991782295391e-06,
      "loss": 0.7836,
      "step": 416
    },
    {
      "epoch": 0.005543351467758499,
      "grad_norm": 0.7595654129981995,
      "learning_rate": 7.197918854261432e-06,
      "loss": 0.784,
      "step": 417
    },
    {
      "epoch": 0.005556644876554082,
      "grad_norm": 0.7038994431495667,
      "learning_rate": 7.029679424927365e-06,
      "loss": 0.799,
      "step": 418
    },
    {
      "epoch": 0.005569938285349667,
      "grad_norm": 0.8161758780479431,
      "learning_rate": 6.863280701110408e-06,
      "loss": 0.7753,
      "step": 419
    },
    {
      "epoch": 0.00558323169414525,
      "grad_norm": 0.7890415191650391,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.8616,
      "step": 420
    },
    {
      "epoch": 0.0055965251029408344,
      "grad_norm": 0.7748125195503235,
      "learning_rate": 6.536033802742813e-06,
      "loss": 0.8245,
      "step": 421
    },
    {
      "epoch": 0.005609818511736418,
      "grad_norm": 0.7969025373458862,
      "learning_rate": 6.375199646360142e-06,
      "loss": 0.8565,
      "step": 422
    },
    {
      "epoch": 0.005623111920532002,
      "grad_norm": 0.8649901151657104,
      "learning_rate": 6.216234231230012e-06,
      "loss": 0.7626,
      "step": 423
    },
    {
      "epoch": 0.005636405329327586,
      "grad_norm": 0.9874373078346252,
      "learning_rate": 6.059144366901736e-06,
      "loss": 0.8389,
      "step": 424
    },
    {
      "epoch": 0.00564969873812317,
      "grad_norm": 1.0835766792297363,
      "learning_rate": 5.903936782582253e-06,
      "loss": 0.9118,
      "step": 425
    },
    {
      "epoch": 0.005662992146918754,
      "grad_norm": 0.9118421673774719,
      "learning_rate": 5.750618126847912e-06,
      "loss": 0.7834,
      "step": 426
    },
    {
      "epoch": 0.005676285555714338,
      "grad_norm": 0.8470845222473145,
      "learning_rate": 5.599194967359639e-06,
      "loss": 0.9175,
      "step": 427
    },
    {
      "epoch": 0.005689578964509922,
      "grad_norm": 0.9073331952095032,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.6926,
      "step": 428
    },
    {
      "epoch": 0.005702872373305506,
      "grad_norm": 0.8814385533332825,
      "learning_rate": 5.302061001503394e-06,
      "loss": 0.7417,
      "step": 429
    },
    {
      "epoch": 0.00571616578210109,
      "grad_norm": 0.8356123566627502,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.7357,
      "step": 430
    },
    {
      "epoch": 0.005729459190896674,
      "grad_norm": 0.9383419156074524,
      "learning_rate": 5.012585797388936e-06,
      "loss": 0.7568,
      "step": 431
    },
    {
      "epoch": 0.005742752599692258,
      "grad_norm": 1.0396068096160889,
      "learning_rate": 4.87073578250698e-06,
      "loss": 0.8964,
      "step": 432
    },
    {
      "epoch": 0.005756046008487841,
      "grad_norm": 0.943768322467804,
      "learning_rate": 4.730818955102234e-06,
      "loss": 0.8078,
      "step": 433
    },
    {
      "epoch": 0.005769339417283426,
      "grad_norm": 1.0417028665542603,
      "learning_rate": 4.592841308745932e-06,
      "loss": 0.7028,
      "step": 434
    },
    {
      "epoch": 0.005782632826079009,
      "grad_norm": 0.9930217862129211,
      "learning_rate": 4.456808753941205e-06,
      "loss": 0.7532,
      "step": 435
    },
    {
      "epoch": 0.005795926234874594,
      "grad_norm": 0.96372389793396,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.778,
      "step": 436
    },
    {
      "epoch": 0.005809219643670177,
      "grad_norm": 0.9927554726600647,
      "learning_rate": 4.190602144143207e-06,
      "loss": 0.7152,
      "step": 437
    },
    {
      "epoch": 0.005822513052465761,
      "grad_norm": 1.0342813730239868,
      "learning_rate": 4.06043949255509e-06,
      "loss": 0.6377,
      "step": 438
    },
    {
      "epoch": 0.005835806461261345,
      "grad_norm": 1.0414509773254395,
      "learning_rate": 3.932244738840379e-06,
      "loss": 0.6376,
      "step": 439
    },
    {
      "epoch": 0.005849099870056929,
      "grad_norm": 1.107492208480835,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.6948,
      "step": 440
    },
    {
      "epoch": 0.005862393278852513,
      "grad_norm": 1.1170679330825806,
      "learning_rate": 3.681780806244095e-06,
      "loss": 0.7437,
      "step": 441
    },
    {
      "epoch": 0.005875686687648097,
      "grad_norm": 1.1103891134262085,
      "learning_rate": 3.5595223564037884e-06,
      "loss": 0.7499,
      "step": 442
    },
    {
      "epoch": 0.0058889800964436806,
      "grad_norm": 1.24330735206604,
      "learning_rate": 3.4392532620598216e-06,
      "loss": 0.6334,
      "step": 443
    },
    {
      "epoch": 0.005902273505239265,
      "grad_norm": 1.3449854850769043,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 0.7968,
      "step": 444
    },
    {
      "epoch": 0.005915566914034848,
      "grad_norm": 1.3204176425933838,
      "learning_rate": 3.2047036621337236e-06,
      "loss": 0.6635,
      "step": 445
    },
    {
      "epoch": 0.005928860322830433,
      "grad_norm": 1.2414649724960327,
      "learning_rate": 3.0904332038757977e-06,
      "loss": 0.7295,
      "step": 446
    },
    {
      "epoch": 0.005942153731626016,
      "grad_norm": 1.5263049602508545,
      "learning_rate": 2.978172195332263e-06,
      "loss": 0.7899,
      "step": 447
    },
    {
      "epoch": 0.0059554471404216006,
      "grad_norm": 1.4617761373519897,
      "learning_rate": 2.8679254453910785e-06,
      "loss": 0.9122,
      "step": 448
    },
    {
      "epoch": 0.005968740549217184,
      "grad_norm": 1.6838090419769287,
      "learning_rate": 2.759697676656098e-06,
      "loss": 0.64,
      "step": 449
    },
    {
      "epoch": 0.005982033958012768,
      "grad_norm": 2.6550161838531494,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.8126,
      "step": 450
    },
    {
      "epoch": 0.005995327366808352,
      "grad_norm": 0.37697362899780273,
      "learning_rate": 2.549317540589308e-06,
      "loss": 0.8715,
      "step": 451
    },
    {
      "epoch": 0.006008620775603936,
      "grad_norm": 0.5114825963973999,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.9097,
      "step": 452
    },
    {
      "epoch": 0.00602191418439952,
      "grad_norm": 0.9041467905044556,
      "learning_rate": 2.3470678346851518e-06,
      "loss": 0.7524,
      "step": 453
    },
    {
      "epoch": 0.006035207593195104,
      "grad_norm": 0.6717054843902588,
      "learning_rate": 2.2490027771406687e-06,
      "loss": 1.0211,
      "step": 454
    },
    {
      "epoch": 0.006048501001990688,
      "grad_norm": 0.7875092029571533,
      "learning_rate": 2.152983213389559e-06,
      "loss": 0.9721,
      "step": 455
    },
    {
      "epoch": 0.006061794410786272,
      "grad_norm": 0.5727041959762573,
      "learning_rate": 2.0590132565903476e-06,
      "loss": 0.9011,
      "step": 456
    },
    {
      "epoch": 0.006075087819581856,
      "grad_norm": 0.7041869163513184,
      "learning_rate": 1.9670969321032407e-06,
      "loss": 0.7107,
      "step": 457
    },
    {
      "epoch": 0.00608838122837744,
      "grad_norm": 0.6156165599822998,
      "learning_rate": 1.8772381773176417e-06,
      "loss": 0.9564,
      "step": 458
    },
    {
      "epoch": 0.006101674637173024,
      "grad_norm": 0.7087550759315491,
      "learning_rate": 1.7894408414835362e-06,
      "loss": 0.7426,
      "step": 459
    },
    {
      "epoch": 0.0061149680459686075,
      "grad_norm": 0.6475067138671875,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.9619,
      "step": 460
    },
    {
      "epoch": 0.006128261454764192,
      "grad_norm": 0.6087029576301575,
      "learning_rate": 1.620045381987012e-06,
      "loss": 0.7861,
      "step": 461
    },
    {
      "epoch": 0.006141554863559775,
      "grad_norm": 0.7449685335159302,
      "learning_rate": 1.5384545146622852e-06,
      "loss": 0.8359,
      "step": 462
    },
    {
      "epoch": 0.00615484827235536,
      "grad_norm": 0.6803917288780212,
      "learning_rate": 1.4589395786535953e-06,
      "loss": 0.8678,
      "step": 463
    },
    {
      "epoch": 0.006168141681150943,
      "grad_norm": 0.7641089558601379,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 0.7741,
      "step": 464
    },
    {
      "epoch": 0.0061814350899465275,
      "grad_norm": 0.6775990128517151,
      "learning_rate": 1.3061510361333185e-06,
      "loss": 0.8723,
      "step": 465
    },
    {
      "epoch": 0.006194728498742111,
      "grad_norm": 0.7013960480690002,
      "learning_rate": 1.232883974574367e-06,
      "loss": 0.773,
      "step": 466
    },
    {
      "epoch": 0.006208021907537695,
      "grad_norm": 0.776786208152771,
      "learning_rate": 1.1617059339563807e-06,
      "loss": 0.8559,
      "step": 467
    },
    {
      "epoch": 0.006221315316333279,
      "grad_norm": 0.7775864601135254,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.9041,
      "step": 468
    },
    {
      "epoch": 0.006234608725128863,
      "grad_norm": 0.7506851553916931,
      "learning_rate": 1.0256290220474307e-06,
      "loss": 0.8435,
      "step": 469
    },
    {
      "epoch": 0.006247902133924447,
      "grad_norm": 0.7386621236801147,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.7473,
      "step": 470
    },
    {
      "epoch": 0.006261195542720031,
      "grad_norm": 0.7993509769439697,
      "learning_rate": 8.979436164848088e-07,
      "loss": 0.7489,
      "step": 471
    },
    {
      "epoch": 0.0062744889515156145,
      "grad_norm": 0.7552006840705872,
      "learning_rate": 8.372546218022747e-07,
      "loss": 0.7127,
      "step": 472
    },
    {
      "epoch": 0.006287782360311199,
      "grad_norm": 0.7693676352500916,
      "learning_rate": 7.786715955054203e-07,
      "loss": 0.5929,
      "step": 473
    },
    {
      "epoch": 0.006301075769106782,
      "grad_norm": 0.815386950969696,
      "learning_rate": 7.221970470961125e-07,
      "loss": 0.7111,
      "step": 474
    },
    {
      "epoch": 0.006314369177902367,
      "grad_norm": 0.8880845904350281,
      "learning_rate": 6.678333957560512e-07,
      "loss": 0.8529,
      "step": 475
    },
    {
      "epoch": 0.00632766258669795,
      "grad_norm": 0.8343062400817871,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.757,
      "step": 476
    },
    {
      "epoch": 0.0063409559954935345,
      "grad_norm": 0.8290151357650757,
      "learning_rate": 5.654480087916303e-07,
      "loss": 0.7969,
      "step": 477
    },
    {
      "epoch": 0.006354249404289118,
      "grad_norm": 0.897857129573822,
      "learning_rate": 5.174306590164879e-07,
      "loss": 0.8043,
      "step": 478
    },
    {
      "epoch": 0.006367542813084702,
      "grad_norm": 0.8593537211418152,
      "learning_rate": 4.715329778211375e-07,
      "loss": 0.7659,
      "step": 479
    },
    {
      "epoch": 0.006380836221880286,
      "grad_norm": 0.9188363552093506,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.8651,
      "step": 480
    },
    {
      "epoch": 0.00639412963067587,
      "grad_norm": 0.9337843060493469,
      "learning_rate": 3.8610439470164737e-07,
      "loss": 0.6921,
      "step": 481
    },
    {
      "epoch": 0.006407423039471454,
      "grad_norm": 1.0456016063690186,
      "learning_rate": 3.465771522536854e-07,
      "loss": 0.9062,
      "step": 482
    },
    {
      "epoch": 0.006420716448267038,
      "grad_norm": 0.7936729788780212,
      "learning_rate": 3.09176897181096e-07,
      "loss": 0.6508,
      "step": 483
    },
    {
      "epoch": 0.006434009857062622,
      "grad_norm": 1.1638076305389404,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.8091,
      "step": 484
    },
    {
      "epoch": 0.006447303265858206,
      "grad_norm": 1.103006362915039,
      "learning_rate": 2.407636663901591e-07,
      "loss": 0.7818,
      "step": 485
    },
    {
      "epoch": 0.00646059667465379,
      "grad_norm": 0.9680044054985046,
      "learning_rate": 2.0975362126691712e-07,
      "loss": 0.8071,
      "step": 486
    },
    {
      "epoch": 0.006473890083449374,
      "grad_norm": 0.9734976887702942,
      "learning_rate": 1.8087642458373134e-07,
      "loss": 0.7186,
      "step": 487
    },
    {
      "epoch": 0.006487183492244958,
      "grad_norm": 1.012603521347046,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 0.8422,
      "step": 488
    },
    {
      "epoch": 0.0065004769010405415,
      "grad_norm": 1.0326621532440186,
      "learning_rate": 1.2952543313240472e-07,
      "loss": 0.8658,
      "step": 489
    },
    {
      "epoch": 0.006513770309836126,
      "grad_norm": 1.2042450904846191,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.0374,
      "step": 490
    },
    {
      "epoch": 0.006527063718631709,
      "grad_norm": 1.1898421049118042,
      "learning_rate": 8.671949076420882e-08,
      "loss": 0.7595,
      "step": 491
    },
    {
      "epoch": 0.006540357127427294,
      "grad_norm": 1.2077451944351196,
      "learning_rate": 6.852326227130834e-08,
      "loss": 0.7744,
      "step": 492
    },
    {
      "epoch": 0.006553650536222877,
      "grad_norm": 1.251529335975647,
      "learning_rate": 5.246593205699424e-08,
      "loss": 0.5662,
      "step": 493
    },
    {
      "epoch": 0.0065669439450184615,
      "grad_norm": 1.371506690979004,
      "learning_rate": 3.8548187963854956e-08,
      "loss": 0.8208,
      "step": 494
    },
    {
      "epoch": 0.006580237353814045,
      "grad_norm": 1.296230435371399,
      "learning_rate": 2.6770626181715773e-08,
      "loss": 0.8259,
      "step": 495
    },
    {
      "epoch": 0.006593530762609629,
      "grad_norm": 1.438158631324768,
      "learning_rate": 1.7133751222137007e-08,
      "loss": 0.7091,
      "step": 496
    },
    {
      "epoch": 0.006606824171405213,
      "grad_norm": 1.3646377325057983,
      "learning_rate": 9.637975896759077e-09,
      "loss": 0.934,
      "step": 497
    },
    {
      "epoch": 0.006620117580200797,
      "grad_norm": 1.6082695722579956,
      "learning_rate": 4.2836212996499865e-09,
      "loss": 0.8442,
      "step": 498
    },
    {
      "epoch": 0.006633410988996381,
      "grad_norm": 1.5005607604980469,
      "learning_rate": 1.0709167935385455e-09,
      "loss": 0.6807,
      "step": 499
    },
    {
      "epoch": 0.006646704397791965,
      "grad_norm": 2.516221284866333,
      "learning_rate": 0.0,
      "loss": 0.7107,
      "step": 500
    },
    {
      "epoch": 0.006646704397791965,
      "eval_loss": 0.7737080454826355,
      "eval_runtime": 5387.8964,
      "eval_samples_per_second": 23.515,
      "eval_steps_per_second": 5.879,
      "step": 500
    }
  ],
  "logging_steps": 1,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "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": 2.8679806819447603e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}