{
  "best_metric": 0.7565295696258545,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.012584552461853075,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.292276230926537e-05,
      "grad_norm": 5.986400127410889,
      "learning_rate": 7e-06,
      "loss": 3.2186,
      "step": 1
    },
    {
      "epoch": 6.292276230926537e-05,
      "eval_loss": 3.337966203689575,
      "eval_runtime": 1982.4345,
      "eval_samples_per_second": 13.502,
      "eval_steps_per_second": 3.376,
      "step": 1
    },
    {
      "epoch": 0.00012584552461853074,
      "grad_norm": 4.323029041290283,
      "learning_rate": 1.4e-05,
      "loss": 3.1404,
      "step": 2
    },
    {
      "epoch": 0.00018876828692779613,
      "grad_norm": 4.952574253082275,
      "learning_rate": 2.1e-05,
      "loss": 3.2877,
      "step": 3
    },
    {
      "epoch": 0.0002516910492370615,
      "grad_norm": 4.0908002853393555,
      "learning_rate": 2.8e-05,
      "loss": 3.1518,
      "step": 4
    },
    {
      "epoch": 0.0003146138115463269,
      "grad_norm": 4.221651554107666,
      "learning_rate": 3.5e-05,
      "loss": 2.9434,
      "step": 5
    },
    {
      "epoch": 0.00037753657385559226,
      "grad_norm": 3.3892202377319336,
      "learning_rate": 4.2e-05,
      "loss": 2.5067,
      "step": 6
    },
    {
      "epoch": 0.00044045933616485765,
      "grad_norm": 3.718759536743164,
      "learning_rate": 4.899999999999999e-05,
      "loss": 2.3159,
      "step": 7
    },
    {
      "epoch": 0.000503382098474123,
      "grad_norm": 2.939546823501587,
      "learning_rate": 5.6e-05,
      "loss": 2.0392,
      "step": 8
    },
    {
      "epoch": 0.0005663048607833884,
      "grad_norm": 2.607264757156372,
      "learning_rate": 6.3e-05,
      "loss": 1.7058,
      "step": 9
    },
    {
      "epoch": 0.0006292276230926538,
      "grad_norm": 2.196113109588623,
      "learning_rate": 7e-05,
      "loss": 1.553,
      "step": 10
    },
    {
      "epoch": 0.0006921503854019191,
      "grad_norm": 2.2309348583221436,
      "learning_rate": 6.999521567473641e-05,
      "loss": 1.4338,
      "step": 11
    },
    {
      "epoch": 0.0007550731477111845,
      "grad_norm": 2.073564052581787,
      "learning_rate": 6.998086400693241e-05,
      "loss": 1.3111,
      "step": 12
    },
    {
      "epoch": 0.0008179959100204499,
      "grad_norm": 1.8639460802078247,
      "learning_rate": 6.995694892019065e-05,
      "loss": 1.328,
      "step": 13
    },
    {
      "epoch": 0.0008809186723297153,
      "grad_norm": 1.7032676935195923,
      "learning_rate": 6.99234769526571e-05,
      "loss": 1.2365,
      "step": 14
    },
    {
      "epoch": 0.0009438414346389807,
      "grad_norm": 1.5915247201919556,
      "learning_rate": 6.988045725523343e-05,
      "loss": 1.1853,
      "step": 15
    },
    {
      "epoch": 0.001006764196948246,
      "grad_norm": 1.4936903715133667,
      "learning_rate": 6.982790158907539e-05,
      "loss": 1.1614,
      "step": 16
    },
    {
      "epoch": 0.0010696869592575113,
      "grad_norm": 1.7372533082962036,
      "learning_rate": 6.976582432237733e-05,
      "loss": 1.0464,
      "step": 17
    },
    {
      "epoch": 0.0011326097215667767,
      "grad_norm": 1.535237431526184,
      "learning_rate": 6.969424242644413e-05,
      "loss": 1.1127,
      "step": 18
    },
    {
      "epoch": 0.0011955324838760421,
      "grad_norm": 1.3509422540664673,
      "learning_rate": 6.961317547105138e-05,
      "loss": 1.0446,
      "step": 19
    },
    {
      "epoch": 0.0012584552461853075,
      "grad_norm": 1.4028918743133545,
      "learning_rate": 6.952264561909527e-05,
      "loss": 0.9723,
      "step": 20
    },
    {
      "epoch": 0.0013213780084945729,
      "grad_norm": 1.3735560178756714,
      "learning_rate": 6.942267762053337e-05,
      "loss": 0.9461,
      "step": 21
    },
    {
      "epoch": 0.0013843007708038383,
      "grad_norm": 1.4489954710006714,
      "learning_rate": 6.931329880561832e-05,
      "loss": 0.9998,
      "step": 22
    },
    {
      "epoch": 0.0014472235331131037,
      "grad_norm": 1.5044622421264648,
      "learning_rate": 6.919453907742597e-05,
      "loss": 0.9574,
      "step": 23
    },
    {
      "epoch": 0.001510146295422369,
      "grad_norm": 1.3582931756973267,
      "learning_rate": 6.90664309036802e-05,
      "loss": 0.9829,
      "step": 24
    },
    {
      "epoch": 0.0015730690577316344,
      "grad_norm": 1.3072384595870972,
      "learning_rate": 6.892900930787656e-05,
      "loss": 0.9791,
      "step": 25
    },
    {
      "epoch": 0.0016359918200408998,
      "grad_norm": 1.2917894124984741,
      "learning_rate": 6.87823118597072e-05,
      "loss": 0.9295,
      "step": 26
    },
    {
      "epoch": 0.0016989145823501652,
      "grad_norm": 1.3019707202911377,
      "learning_rate": 6.862637866478969e-05,
      "loss": 0.9275,
      "step": 27
    },
    {
      "epoch": 0.0017618373446594306,
      "grad_norm": 1.2621512413024902,
      "learning_rate": 6.846125235370252e-05,
      "loss": 0.9486,
      "step": 28
    },
    {
      "epoch": 0.001824760106968696,
      "grad_norm": 1.2977919578552246,
      "learning_rate": 6.828697807033038e-05,
      "loss": 1.0192,
      "step": 29
    },
    {
      "epoch": 0.0018876828692779614,
      "grad_norm": 1.1111100912094116,
      "learning_rate": 6.81036034595222e-05,
      "loss": 0.9167,
      "step": 30
    },
    {
      "epoch": 0.0019506056315872267,
      "grad_norm": 1.1611779928207397,
      "learning_rate": 6.791117865406564e-05,
      "loss": 0.9082,
      "step": 31
    },
    {
      "epoch": 0.002013528393896492,
      "grad_norm": 1.428572654724121,
      "learning_rate": 6.770975626098112e-05,
      "loss": 0.8713,
      "step": 32
    },
    {
      "epoch": 0.0020764511562057575,
      "grad_norm": 1.3148999214172363,
      "learning_rate": 6.749939134713974e-05,
      "loss": 0.9375,
      "step": 33
    },
    {
      "epoch": 0.0021393739185150227,
      "grad_norm": 1.1416841745376587,
      "learning_rate": 6.728014142420846e-05,
      "loss": 0.8438,
      "step": 34
    },
    {
      "epoch": 0.0022022966808242883,
      "grad_norm": 1.3152703046798706,
      "learning_rate": 6.7052066432927e-05,
      "loss": 0.9086,
      "step": 35
    },
    {
      "epoch": 0.0022652194431335535,
      "grad_norm": 1.1894391775131226,
      "learning_rate": 6.681522872672069e-05,
      "loss": 0.9079,
      "step": 36
    },
    {
      "epoch": 0.002328142205442819,
      "grad_norm": 1.334936261177063,
      "learning_rate": 6.656969305465356e-05,
      "loss": 0.8534,
      "step": 37
    },
    {
      "epoch": 0.0023910649677520842,
      "grad_norm": 1.567651391029358,
      "learning_rate": 6.631552654372672e-05,
      "loss": 0.9743,
      "step": 38
    },
    {
      "epoch": 0.00245398773006135,
      "grad_norm": 1.1267035007476807,
      "learning_rate": 6.60527986805264e-05,
      "loss": 0.8412,
      "step": 39
    },
    {
      "epoch": 0.002516910492370615,
      "grad_norm": 1.1401087045669556,
      "learning_rate": 6.578158129222711e-05,
      "loss": 0.8682,
      "step": 40
    },
    {
      "epoch": 0.0025798332546798806,
      "grad_norm": 1.341891884803772,
      "learning_rate": 6.550194852695469e-05,
      "loss": 0.955,
      "step": 41
    },
    {
      "epoch": 0.0026427560169891458,
      "grad_norm": 1.4082252979278564,
      "learning_rate": 6.521397683351509e-05,
      "loss": 0.9514,
      "step": 42
    },
    {
      "epoch": 0.0027056787792984114,
      "grad_norm": 1.227417230606079,
      "learning_rate": 6.491774494049386e-05,
      "loss": 0.8623,
      "step": 43
    },
    {
      "epoch": 0.0027686015416076766,
      "grad_norm": 1.0718835592269897,
      "learning_rate": 6.461333383473272e-05,
      "loss": 0.8627,
      "step": 44
    },
    {
      "epoch": 0.002831524303916942,
      "grad_norm": 1.0756818056106567,
      "learning_rate": 6.430082673918849e-05,
      "loss": 0.9668,
      "step": 45
    },
    {
      "epoch": 0.0028944470662262073,
      "grad_norm": 1.0300580263137817,
      "learning_rate": 6.398030909018069e-05,
      "loss": 0.9133,
      "step": 46
    },
    {
      "epoch": 0.0029573698285354725,
      "grad_norm": 1.3402928113937378,
      "learning_rate": 6.365186851403423e-05,
      "loss": 0.9259,
      "step": 47
    },
    {
      "epoch": 0.003020292590844738,
      "grad_norm": 1.3988003730773926,
      "learning_rate": 6.331559480312315e-05,
      "loss": 0.8476,
      "step": 48
    },
    {
      "epoch": 0.0030832153531540033,
      "grad_norm": 1.2574834823608398,
      "learning_rate": 6.297157989132236e-05,
      "loss": 0.914,
      "step": 49
    },
    {
      "epoch": 0.003146138115463269,
      "grad_norm": 1.2871612310409546,
      "learning_rate": 6.261991782887377e-05,
      "loss": 0.9743,
      "step": 50
    },
    {
      "epoch": 0.003146138115463269,
      "eval_loss": 1.0053454637527466,
      "eval_runtime": 1992.2887,
      "eval_samples_per_second": 13.435,
      "eval_steps_per_second": 3.359,
      "step": 50
    },
    {
      "epoch": 0.003209060877772534,
      "grad_norm": 2.972357988357544,
      "learning_rate": 6.226070475667393e-05,
      "loss": 1.0407,
      "step": 51
    },
    {
      "epoch": 0.0032719836400817996,
      "grad_norm": 2.400644063949585,
      "learning_rate": 6.189403887999006e-05,
      "loss": 1.0451,
      "step": 52
    },
    {
      "epoch": 0.003334906402391065,
      "grad_norm": 1.9864860773086548,
      "learning_rate": 6.152002044161171e-05,
      "loss": 0.9949,
      "step": 53
    },
    {
      "epoch": 0.0033978291647003304,
      "grad_norm": 1.4594244956970215,
      "learning_rate": 6.113875169444539e-05,
      "loss": 0.868,
      "step": 54
    },
    {
      "epoch": 0.0034607519270095956,
      "grad_norm": 1.3587267398834229,
      "learning_rate": 6.0750336873559605e-05,
      "loss": 0.8936,
      "step": 55
    },
    {
      "epoch": 0.003523674689318861,
      "grad_norm": 1.2400847673416138,
      "learning_rate": 6.035488216768811e-05,
      "loss": 0.8392,
      "step": 56
    },
    {
      "epoch": 0.0035865974516281264,
      "grad_norm": 1.0019475221633911,
      "learning_rate": 5.9952495690198894e-05,
      "loss": 0.8268,
      "step": 57
    },
    {
      "epoch": 0.003649520213937392,
      "grad_norm": 1.0382566452026367,
      "learning_rate": 5.954328744953709e-05,
      "loss": 0.8917,
      "step": 58
    },
    {
      "epoch": 0.003712442976246657,
      "grad_norm": 1.1378562450408936,
      "learning_rate": 5.91273693191498e-05,
      "loss": 0.8212,
      "step": 59
    },
    {
      "epoch": 0.0037753657385559227,
      "grad_norm": 0.9841014742851257,
      "learning_rate": 5.870485500690094e-05,
      "loss": 0.9018,
      "step": 60
    },
    {
      "epoch": 0.003838288500865188,
      "grad_norm": 1.0065339803695679,
      "learning_rate": 5.827586002398468e-05,
      "loss": 0.8772,
      "step": 61
    },
    {
      "epoch": 0.0039012112631744535,
      "grad_norm": 0.8579968214035034,
      "learning_rate": 5.784050165334589e-05,
      "loss": 0.7739,
      "step": 62
    },
    {
      "epoch": 0.003964134025483719,
      "grad_norm": 0.8406140208244324,
      "learning_rate": 5.739889891761608e-05,
      "loss": 0.8281,
      "step": 63
    },
    {
      "epoch": 0.004027056787792984,
      "grad_norm": 0.966905415058136,
      "learning_rate": 5.6951172546573794e-05,
      "loss": 0.8692,
      "step": 64
    },
    {
      "epoch": 0.00408997955010225,
      "grad_norm": 0.7755886912345886,
      "learning_rate": 5.6497444944138376e-05,
      "loss": 0.8057,
      "step": 65
    },
    {
      "epoch": 0.004152902312411515,
      "grad_norm": 0.8802056908607483,
      "learning_rate": 5.603784015490587e-05,
      "loss": 0.826,
      "step": 66
    },
    {
      "epoch": 0.00421582507472078,
      "grad_norm": 0.9546853303909302,
      "learning_rate": 5.557248383023655e-05,
      "loss": 0.8029,
      "step": 67
    },
    {
      "epoch": 0.004278747837030045,
      "grad_norm": 0.9124829173088074,
      "learning_rate": 5.510150319390302e-05,
      "loss": 0.8423,
      "step": 68
    },
    {
      "epoch": 0.004341670599339311,
      "grad_norm": 0.8863704800605774,
      "learning_rate": 5.4625027007308546e-05,
      "loss": 0.8612,
      "step": 69
    },
    {
      "epoch": 0.004404593361648577,
      "grad_norm": 1.0014814138412476,
      "learning_rate": 5.414318553428494e-05,
      "loss": 0.8589,
      "step": 70
    },
    {
      "epoch": 0.004467516123957842,
      "grad_norm": 0.9849516153335571,
      "learning_rate": 5.3656110505479776e-05,
      "loss": 0.8943,
      "step": 71
    },
    {
      "epoch": 0.004530438886267107,
      "grad_norm": 0.9532140493392944,
      "learning_rate": 5.316393508234253e-05,
      "loss": 0.8828,
      "step": 72
    },
    {
      "epoch": 0.004593361648576372,
      "grad_norm": 0.8421981334686279,
      "learning_rate": 5.266679382071953e-05,
      "loss": 0.8656,
      "step": 73
    },
    {
      "epoch": 0.004656284410885638,
      "grad_norm": 0.8308148980140686,
      "learning_rate": 5.216482263406778e-05,
      "loss": 0.8772,
      "step": 74
    },
    {
      "epoch": 0.004719207173194903,
      "grad_norm": 0.8596946597099304,
      "learning_rate": 5.1658158756297576e-05,
      "loss": 0.7459,
      "step": 75
    },
    {
      "epoch": 0.0047821299355041685,
      "grad_norm": 0.9619783759117126,
      "learning_rate": 5.114694070425407e-05,
      "loss": 0.7956,
      "step": 76
    },
    {
      "epoch": 0.004845052697813434,
      "grad_norm": 0.7666736841201782,
      "learning_rate": 5.063130823984823e-05,
      "loss": 0.8107,
      "step": 77
    },
    {
      "epoch": 0.0049079754601227,
      "grad_norm": 0.8894594311714172,
      "learning_rate": 5.011140233184724e-05,
      "loss": 0.7947,
      "step": 78
    },
    {
      "epoch": 0.004970898222431965,
      "grad_norm": 0.892618715763092,
      "learning_rate": 4.958736511733516e-05,
      "loss": 0.8174,
      "step": 79
    },
    {
      "epoch": 0.00503382098474123,
      "grad_norm": 0.8254565596580505,
      "learning_rate": 4.905933986285393e-05,
      "loss": 0.7955,
      "step": 80
    },
    {
      "epoch": 0.005096743747050495,
      "grad_norm": 0.8944692611694336,
      "learning_rate": 4.8527470925235824e-05,
      "loss": 0.7174,
      "step": 81
    },
    {
      "epoch": 0.005159666509359761,
      "grad_norm": 0.879101037979126,
      "learning_rate": 4.799190371213772e-05,
      "loss": 0.8039,
      "step": 82
    },
    {
      "epoch": 0.005222589271669026,
      "grad_norm": 1.0178143978118896,
      "learning_rate": 4.745278464228808e-05,
      "loss": 0.7782,
      "step": 83
    },
    {
      "epoch": 0.0052855120339782916,
      "grad_norm": 0.9104377627372742,
      "learning_rate": 4.69102611054575e-05,
      "loss": 0.7746,
      "step": 84
    },
    {
      "epoch": 0.005348434796287557,
      "grad_norm": 0.8293485641479492,
      "learning_rate": 4.6364481422163926e-05,
      "loss": 0.8368,
      "step": 85
    },
    {
      "epoch": 0.005411357558596823,
      "grad_norm": 0.7431213855743408,
      "learning_rate": 4.581559480312316e-05,
      "loss": 0.7825,
      "step": 86
    },
    {
      "epoch": 0.005474280320906088,
      "grad_norm": 0.843418538570404,
      "learning_rate": 4.526375130845627e-05,
      "loss": 0.7644,
      "step": 87
    },
    {
      "epoch": 0.005537203083215353,
      "grad_norm": 0.9385837912559509,
      "learning_rate": 4.4709101806664554e-05,
      "loss": 0.8535,
      "step": 88
    },
    {
      "epoch": 0.005600125845524618,
      "grad_norm": 1.0642012357711792,
      "learning_rate": 4.4151797933383685e-05,
      "loss": 0.863,
      "step": 89
    },
    {
      "epoch": 0.005663048607833884,
      "grad_norm": 0.8669362664222717,
      "learning_rate": 4.359199204992797e-05,
      "loss": 0.7873,
      "step": 90
    },
    {
      "epoch": 0.0057259713701431495,
      "grad_norm": 0.8444873094558716,
      "learning_rate": 4.30298372016363e-05,
      "loss": 0.8437,
      "step": 91
    },
    {
      "epoch": 0.005788894132452415,
      "grad_norm": 0.9069030284881592,
      "learning_rate": 4.246548707603114e-05,
      "loss": 0.8153,
      "step": 92
    },
    {
      "epoch": 0.00585181689476168,
      "grad_norm": 0.9278481006622314,
      "learning_rate": 4.1899095960801805e-05,
      "loss": 0.8287,
      "step": 93
    },
    {
      "epoch": 0.005914739657070945,
      "grad_norm": 0.9167292714118958,
      "learning_rate": 4.133081870162385e-05,
      "loss": 0.8283,
      "step": 94
    },
    {
      "epoch": 0.005977662419380211,
      "grad_norm": 0.9848026037216187,
      "learning_rate": 4.076081065982569e-05,
      "loss": 0.81,
      "step": 95
    },
    {
      "epoch": 0.006040585181689476,
      "grad_norm": 0.9342053532600403,
      "learning_rate": 4.018922766991447e-05,
      "loss": 0.8198,
      "step": 96
    },
    {
      "epoch": 0.006103507943998741,
      "grad_norm": 0.9642012715339661,
      "learning_rate": 3.961622599697241e-05,
      "loss": 0.8798,
      "step": 97
    },
    {
      "epoch": 0.0061664307063080065,
      "grad_norm": 1.2058335542678833,
      "learning_rate": 3.9041962293935516e-05,
      "loss": 0.8116,
      "step": 98
    },
    {
      "epoch": 0.0062293534686172726,
      "grad_norm": 1.0484851598739624,
      "learning_rate": 3.84665935587662e-05,
      "loss": 0.827,
      "step": 99
    },
    {
      "epoch": 0.006292276230926538,
      "grad_norm": 1.195165753364563,
      "learning_rate": 3.7890277091531636e-05,
      "loss": 1.0012,
      "step": 100
    },
    {
      "epoch": 0.006292276230926538,
      "eval_loss": 0.8752425312995911,
      "eval_runtime": 1993.4601,
      "eval_samples_per_second": 13.427,
      "eval_steps_per_second": 3.357,
      "step": 100
    },
    {
      "epoch": 0.006355198993235803,
      "grad_norm": 2.021313428878784,
      "learning_rate": 3.7313170451399475e-05,
      "loss": 1.0507,
      "step": 101
    },
    {
      "epoch": 0.006418121755545068,
      "grad_norm": 1.4400451183319092,
      "learning_rate": 3.673543141356278e-05,
      "loss": 0.796,
      "step": 102
    },
    {
      "epoch": 0.006481044517854334,
      "grad_norm": 1.2445330619812012,
      "learning_rate": 3.6157217926105783e-05,
      "loss": 0.8111,
      "step": 103
    },
    {
      "epoch": 0.006543967280163599,
      "grad_norm": 1.1896748542785645,
      "learning_rate": 3.557868806682255e-05,
      "loss": 0.8734,
      "step": 104
    },
    {
      "epoch": 0.0066068900424728644,
      "grad_norm": 0.9736097455024719,
      "learning_rate": 3.5e-05,
      "loss": 0.7701,
      "step": 105
    },
    {
      "epoch": 0.00666981280478213,
      "grad_norm": 0.828886091709137,
      "learning_rate": 3.442131193317745e-05,
      "loss": 0.8266,
      "step": 106
    },
    {
      "epoch": 0.006732735567091396,
      "grad_norm": 0.8219014406204224,
      "learning_rate": 3.384278207389421e-05,
      "loss": 0.7893,
      "step": 107
    },
    {
      "epoch": 0.006795658329400661,
      "grad_norm": 0.7297405004501343,
      "learning_rate": 3.3264568586437216e-05,
      "loss": 0.8185,
      "step": 108
    },
    {
      "epoch": 0.006858581091709926,
      "grad_norm": 0.8358471989631653,
      "learning_rate": 3.268682954860052e-05,
      "loss": 0.8146,
      "step": 109
    },
    {
      "epoch": 0.006921503854019191,
      "grad_norm": 0.8461059331893921,
      "learning_rate": 3.210972290846837e-05,
      "loss": 0.823,
      "step": 110
    },
    {
      "epoch": 0.006984426616328457,
      "grad_norm": 0.8077146410942078,
      "learning_rate": 3.15334064412338e-05,
      "loss": 0.7864,
      "step": 111
    },
    {
      "epoch": 0.007047349378637722,
      "grad_norm": 0.7723516821861267,
      "learning_rate": 3.0958037706064485e-05,
      "loss": 0.7792,
      "step": 112
    },
    {
      "epoch": 0.0071102721409469875,
      "grad_norm": 0.8124366998672485,
      "learning_rate": 3.038377400302758e-05,
      "loss": 0.7783,
      "step": 113
    },
    {
      "epoch": 0.007173194903256253,
      "grad_norm": 0.7554612159729004,
      "learning_rate": 2.9810772330085524e-05,
      "loss": 0.7939,
      "step": 114
    },
    {
      "epoch": 0.007236117665565519,
      "grad_norm": 0.8711295127868652,
      "learning_rate": 2.9239189340174306e-05,
      "loss": 0.7831,
      "step": 115
    },
    {
      "epoch": 0.007299040427874784,
      "grad_norm": 0.8391959071159363,
      "learning_rate": 2.8669181298376163e-05,
      "loss": 0.7695,
      "step": 116
    },
    {
      "epoch": 0.007361963190184049,
      "grad_norm": 0.8773452043533325,
      "learning_rate": 2.8100904039198193e-05,
      "loss": 0.7739,
      "step": 117
    },
    {
      "epoch": 0.007424885952493314,
      "grad_norm": 0.7932614088058472,
      "learning_rate": 2.7534512923968863e-05,
      "loss": 0.7563,
      "step": 118
    },
    {
      "epoch": 0.007487808714802579,
      "grad_norm": 0.8110454678535461,
      "learning_rate": 2.6970162798363695e-05,
      "loss": 0.837,
      "step": 119
    },
    {
      "epoch": 0.0075507314771118455,
      "grad_norm": 0.7787162065505981,
      "learning_rate": 2.640800795007203e-05,
      "loss": 0.7379,
      "step": 120
    },
    {
      "epoch": 0.007613654239421111,
      "grad_norm": 0.8096684217453003,
      "learning_rate": 2.5848202066616305e-05,
      "loss": 0.7867,
      "step": 121
    },
    {
      "epoch": 0.007676577001730376,
      "grad_norm": 0.7443400025367737,
      "learning_rate": 2.5290898193335446e-05,
      "loss": 0.7363,
      "step": 122
    },
    {
      "epoch": 0.007739499764039641,
      "grad_norm": 0.7531337141990662,
      "learning_rate": 2.4736248691543736e-05,
      "loss": 0.7771,
      "step": 123
    },
    {
      "epoch": 0.007802422526348907,
      "grad_norm": 0.7670841813087463,
      "learning_rate": 2.4184405196876842e-05,
      "loss": 0.7493,
      "step": 124
    },
    {
      "epoch": 0.007865345288658171,
      "grad_norm": 0.8572217226028442,
      "learning_rate": 2.363551857783608e-05,
      "loss": 0.7938,
      "step": 125
    },
    {
      "epoch": 0.007928268050967437,
      "grad_norm": 0.7786096334457397,
      "learning_rate": 2.308973889454249e-05,
      "loss": 0.7789,
      "step": 126
    },
    {
      "epoch": 0.007991190813276703,
      "grad_norm": 0.8275337219238281,
      "learning_rate": 2.2547215357711918e-05,
      "loss": 0.7598,
      "step": 127
    },
    {
      "epoch": 0.008054113575585968,
      "grad_norm": 0.8422858119010925,
      "learning_rate": 2.2008096287862266e-05,
      "loss": 0.8221,
      "step": 128
    },
    {
      "epoch": 0.008117036337895234,
      "grad_norm": 0.7570464611053467,
      "learning_rate": 2.1472529074764177e-05,
      "loss": 0.7552,
      "step": 129
    },
    {
      "epoch": 0.0081799591002045,
      "grad_norm": 0.7353229522705078,
      "learning_rate": 2.0940660137146074e-05,
      "loss": 0.7386,
      "step": 130
    },
    {
      "epoch": 0.008242881862513764,
      "grad_norm": 0.7655825018882751,
      "learning_rate": 2.041263488266484e-05,
      "loss": 0.7613,
      "step": 131
    },
    {
      "epoch": 0.00830580462482303,
      "grad_norm": 0.8073829412460327,
      "learning_rate": 1.988859766815275e-05,
      "loss": 0.7178,
      "step": 132
    },
    {
      "epoch": 0.008368727387132294,
      "grad_norm": 0.7817210555076599,
      "learning_rate": 1.9368691760151773e-05,
      "loss": 0.771,
      "step": 133
    },
    {
      "epoch": 0.00843165014944156,
      "grad_norm": 0.7924845218658447,
      "learning_rate": 1.885305929574593e-05,
      "loss": 0.7991,
      "step": 134
    },
    {
      "epoch": 0.008494572911750826,
      "grad_norm": 0.8270777463912964,
      "learning_rate": 1.8341841243702424e-05,
      "loss": 0.8183,
      "step": 135
    },
    {
      "epoch": 0.00855749567406009,
      "grad_norm": 0.8548717498779297,
      "learning_rate": 1.7835177365932225e-05,
      "loss": 0.7226,
      "step": 136
    },
    {
      "epoch": 0.008620418436369357,
      "grad_norm": 1.0007916688919067,
      "learning_rate": 1.7333206179280478e-05,
      "loss": 0.8753,
      "step": 137
    },
    {
      "epoch": 0.008683341198678623,
      "grad_norm": 0.786884069442749,
      "learning_rate": 1.6836064917657478e-05,
      "loss": 0.7939,
      "step": 138
    },
    {
      "epoch": 0.008746263960987887,
      "grad_norm": 0.7700645923614502,
      "learning_rate": 1.6343889494520224e-05,
      "loss": 0.6812,
      "step": 139
    },
    {
      "epoch": 0.008809186723297153,
      "grad_norm": 0.8353739380836487,
      "learning_rate": 1.5856814465715064e-05,
      "loss": 0.8099,
      "step": 140
    },
    {
      "epoch": 0.008872109485606417,
      "grad_norm": 0.883284330368042,
      "learning_rate": 1.5374972992691458e-05,
      "loss": 0.8062,
      "step": 141
    },
    {
      "epoch": 0.008935032247915684,
      "grad_norm": 0.7576009035110474,
      "learning_rate": 1.4898496806096974e-05,
      "loss": 0.7673,
      "step": 142
    },
    {
      "epoch": 0.00899795501022495,
      "grad_norm": 0.790837287902832,
      "learning_rate": 1.4427516169763444e-05,
      "loss": 0.808,
      "step": 143
    },
    {
      "epoch": 0.009060877772534214,
      "grad_norm": 0.790503740310669,
      "learning_rate": 1.396215984509412e-05,
      "loss": 0.8153,
      "step": 144
    },
    {
      "epoch": 0.00912380053484348,
      "grad_norm": 0.8170227408409119,
      "learning_rate": 1.3502555055861625e-05,
      "loss": 0.7711,
      "step": 145
    },
    {
      "epoch": 0.009186723297152744,
      "grad_norm": 0.8592228293418884,
      "learning_rate": 1.3048827453426203e-05,
      "loss": 0.8427,
      "step": 146
    },
    {
      "epoch": 0.00924964605946201,
      "grad_norm": 0.8412076830863953,
      "learning_rate": 1.2601101082383917e-05,
      "loss": 0.7799,
      "step": 147
    },
    {
      "epoch": 0.009312568821771276,
      "grad_norm": 0.9095844626426697,
      "learning_rate": 1.2159498346654094e-05,
      "loss": 0.8593,
      "step": 148
    },
    {
      "epoch": 0.00937549158408054,
      "grad_norm": 0.9096418619155884,
      "learning_rate": 1.1724139976015306e-05,
      "loss": 0.8268,
      "step": 149
    },
    {
      "epoch": 0.009438414346389807,
      "grad_norm": 1.1173503398895264,
      "learning_rate": 1.1295144993099068e-05,
      "loss": 0.9194,
      "step": 150
    },
    {
      "epoch": 0.009438414346389807,
      "eval_loss": 0.797228217124939,
      "eval_runtime": 1992.4696,
      "eval_samples_per_second": 13.434,
      "eval_steps_per_second": 3.359,
      "step": 150
    },
    {
      "epoch": 0.009501337108699073,
      "grad_norm": 1.1855599880218506,
      "learning_rate": 1.0872630680850196e-05,
      "loss": 0.8064,
      "step": 151
    },
    {
      "epoch": 0.009564259871008337,
      "grad_norm": 0.9709980487823486,
      "learning_rate": 1.0456712550462898e-05,
      "loss": 0.7101,
      "step": 152
    },
    {
      "epoch": 0.009627182633317603,
      "grad_norm": 1.1739250421524048,
      "learning_rate": 1.0047504309801104e-05,
      "loss": 0.8683,
      "step": 153
    },
    {
      "epoch": 0.009690105395626867,
      "grad_norm": 0.9647789597511292,
      "learning_rate": 9.645117832311886e-06,
      "loss": 0.7801,
      "step": 154
    },
    {
      "epoch": 0.009753028157936133,
      "grad_norm": 0.944773256778717,
      "learning_rate": 9.249663126440394e-06,
      "loss": 0.8862,
      "step": 155
    },
    {
      "epoch": 0.0098159509202454,
      "grad_norm": 0.9934294819831848,
      "learning_rate": 8.861248305554624e-06,
      "loss": 0.8355,
      "step": 156
    },
    {
      "epoch": 0.009878873682554664,
      "grad_norm": 0.9183503985404968,
      "learning_rate": 8.47997955838829e-06,
      "loss": 0.7931,
      "step": 157
    },
    {
      "epoch": 0.00994179644486393,
      "grad_norm": 0.7778875231742859,
      "learning_rate": 8.10596112000994e-06,
      "loss": 0.7604,
      "step": 158
    },
    {
      "epoch": 0.010004719207173196,
      "grad_norm": 0.8117092251777649,
      "learning_rate": 7.739295243326067e-06,
      "loss": 0.7783,
      "step": 159
    },
    {
      "epoch": 0.01006764196948246,
      "grad_norm": 0.8418658375740051,
      "learning_rate": 7.380082171126228e-06,
      "loss": 0.7706,
      "step": 160
    },
    {
      "epoch": 0.010130564731791726,
      "grad_norm": 0.7367555499076843,
      "learning_rate": 7.028420108677635e-06,
      "loss": 0.7916,
      "step": 161
    },
    {
      "epoch": 0.01019348749410099,
      "grad_norm": 0.6959548592567444,
      "learning_rate": 6.684405196876842e-06,
      "loss": 0.7213,
      "step": 162
    },
    {
      "epoch": 0.010256410256410256,
      "grad_norm": 0.7650184631347656,
      "learning_rate": 6.3481314859657675e-06,
      "loss": 0.848,
      "step": 163
    },
    {
      "epoch": 0.010319333018719522,
      "grad_norm": 0.7810686230659485,
      "learning_rate": 6.019690909819298e-06,
      "loss": 0.7893,
      "step": 164
    },
    {
      "epoch": 0.010382255781028787,
      "grad_norm": 0.6944038271903992,
      "learning_rate": 5.6991732608115e-06,
      "loss": 0.699,
      "step": 165
    },
    {
      "epoch": 0.010445178543338053,
      "grad_norm": 0.7327795624732971,
      "learning_rate": 5.386666165267256e-06,
      "loss": 0.684,
      "step": 166
    },
    {
      "epoch": 0.010508101305647317,
      "grad_norm": 0.780702531337738,
      "learning_rate": 5.08225505950613e-06,
      "loss": 0.749,
      "step": 167
    },
    {
      "epoch": 0.010571024067956583,
      "grad_norm": 0.7373425364494324,
      "learning_rate": 4.786023166484913e-06,
      "loss": 0.7612,
      "step": 168
    },
    {
      "epoch": 0.01063394683026585,
      "grad_norm": 0.718101441860199,
      "learning_rate": 4.498051473045291e-06,
      "loss": 0.7328,
      "step": 169
    },
    {
      "epoch": 0.010696869592575113,
      "grad_norm": 0.7251747250556946,
      "learning_rate": 4.218418707772886e-06,
      "loss": 0.7313,
      "step": 170
    },
    {
      "epoch": 0.01075979235488438,
      "grad_norm": 0.7674394845962524,
      "learning_rate": 3.947201319473587e-06,
      "loss": 0.7357,
      "step": 171
    },
    {
      "epoch": 0.010822715117193646,
      "grad_norm": 0.7181996703147888,
      "learning_rate": 3.684473456273278e-06,
      "loss": 0.7163,
      "step": 172
    },
    {
      "epoch": 0.01088563787950291,
      "grad_norm": 0.7485051155090332,
      "learning_rate": 3.4303069453464383e-06,
      "loss": 0.6467,
      "step": 173
    },
    {
      "epoch": 0.010948560641812176,
      "grad_norm": 0.7699400782585144,
      "learning_rate": 3.184771273279312e-06,
      "loss": 0.7171,
      "step": 174
    },
    {
      "epoch": 0.01101148340412144,
      "grad_norm": 0.7506479620933533,
      "learning_rate": 2.947933567072987e-06,
      "loss": 0.7124,
      "step": 175
    },
    {
      "epoch": 0.011074406166430706,
      "grad_norm": 0.7845705151557922,
      "learning_rate": 2.719858575791534e-06,
      "loss": 0.7512,
      "step": 176
    },
    {
      "epoch": 0.011137328928739972,
      "grad_norm": 0.7802093625068665,
      "learning_rate": 2.500608652860256e-06,
      "loss": 0.7505,
      "step": 177
    },
    {
      "epoch": 0.011200251691049237,
      "grad_norm": 0.7702093124389648,
      "learning_rate": 2.2902437390188737e-06,
      "loss": 0.7246,
      "step": 178
    },
    {
      "epoch": 0.011263174453358503,
      "grad_norm": 0.7330029010772705,
      "learning_rate": 2.0888213459343587e-06,
      "loss": 0.6607,
      "step": 179
    },
    {
      "epoch": 0.011326097215667769,
      "grad_norm": 0.7918237447738647,
      "learning_rate": 1.8963965404777875e-06,
      "loss": 0.7906,
      "step": 180
    },
    {
      "epoch": 0.011389019977977033,
      "grad_norm": 0.7300527095794678,
      "learning_rate": 1.7130219296696263e-06,
      "loss": 0.7848,
      "step": 181
    },
    {
      "epoch": 0.011451942740286299,
      "grad_norm": 0.8390794396400452,
      "learning_rate": 1.5387476462974824e-06,
      "loss": 0.7808,
      "step": 182
    },
    {
      "epoch": 0.011514865502595563,
      "grad_norm": 0.7718068361282349,
      "learning_rate": 1.3736213352103147e-06,
      "loss": 0.7544,
      "step": 183
    },
    {
      "epoch": 0.01157778826490483,
      "grad_norm": 0.7651385068893433,
      "learning_rate": 1.2176881402928002e-06,
      "loss": 0.7245,
      "step": 184
    },
    {
      "epoch": 0.011640711027214095,
      "grad_norm": 0.7763552069664001,
      "learning_rate": 1.0709906921234367e-06,
      "loss": 0.7252,
      "step": 185
    },
    {
      "epoch": 0.01170363378952336,
      "grad_norm": 0.7964072823524475,
      "learning_rate": 9.33569096319799e-07,
      "loss": 0.7854,
      "step": 186
    },
    {
      "epoch": 0.011766556551832626,
      "grad_norm": 0.8242265582084656,
      "learning_rate": 8.054609225740255e-07,
      "loss": 0.7468,
      "step": 187
    },
    {
      "epoch": 0.01182947931414189,
      "grad_norm": 0.8895198106765747,
      "learning_rate": 6.867011943816724e-07,
      "loss": 0.804,
      "step": 188
    },
    {
      "epoch": 0.011892402076451156,
      "grad_norm": 0.8039786219596863,
      "learning_rate": 5.77322379466617e-07,
      "loss": 0.7374,
      "step": 189
    },
    {
      "epoch": 0.011955324838760422,
      "grad_norm": 0.9118459820747375,
      "learning_rate": 4.773543809047186e-07,
      "loss": 0.8076,
      "step": 190
    },
    {
      "epoch": 0.012018247601069686,
      "grad_norm": 0.9070056080818176,
      "learning_rate": 3.868245289486027e-07,
      "loss": 0.7622,
      "step": 191
    },
    {
      "epoch": 0.012081170363378952,
      "grad_norm": 0.8863012194633484,
      "learning_rate": 3.0575757355586817e-07,
      "loss": 0.7473,
      "step": 192
    },
    {
      "epoch": 0.012144093125688218,
      "grad_norm": 0.9500631093978882,
      "learning_rate": 2.3417567762266497e-07,
      "loss": 0.7609,
      "step": 193
    },
    {
      "epoch": 0.012207015887997483,
      "grad_norm": 0.9818147420883179,
      "learning_rate": 1.7209841092460043e-07,
      "loss": 0.8126,
      "step": 194
    },
    {
      "epoch": 0.012269938650306749,
      "grad_norm": 0.9193422198295593,
      "learning_rate": 1.1954274476655534e-07,
      "loss": 0.7631,
      "step": 195
    },
    {
      "epoch": 0.012332861412616013,
      "grad_norm": 1.21839439868927,
      "learning_rate": 7.652304734289127e-08,
      "loss": 0.9298,
      "step": 196
    },
    {
      "epoch": 0.012395784174925279,
      "grad_norm": 1.1351546049118042,
      "learning_rate": 4.30510798093342e-08,
      "loss": 0.8287,
      "step": 197
    },
    {
      "epoch": 0.012458706937234545,
      "grad_norm": 1.1663342714309692,
      "learning_rate": 1.9135993067588284e-08,
      "loss": 0.8636,
      "step": 198
    },
    {
      "epoch": 0.01252162969954381,
      "grad_norm": 1.3851702213287354,
      "learning_rate": 4.784325263584854e-09,
      "loss": 0.9535,
      "step": 199
    },
    {
      "epoch": 0.012584552461853075,
      "grad_norm": 1.7710238695144653,
      "learning_rate": 0.0,
      "loss": 0.967,
      "step": 200
    },
    {
      "epoch": 0.012584552461853075,
      "eval_loss": 0.7565295696258545,
      "eval_runtime": 1993.4631,
      "eval_samples_per_second": 13.427,
      "eval_steps_per_second": 3.357,
      "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": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.017027157491712e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}