{
  "best_metric": 1.4884361028671265,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.0161033837235049,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.051691861752451e-05,
      "grad_norm": 15.297965049743652,
      "learning_rate": 1e-05,
      "loss": 2.23,
      "step": 1
    },
    {
      "epoch": 8.051691861752451e-05,
      "eval_loss": 3.512342929840088,
      "eval_runtime": 1563.3317,
      "eval_samples_per_second": 13.38,
      "eval_steps_per_second": 3.345,
      "step": 1
    },
    {
      "epoch": 0.00016103383723504902,
      "grad_norm": 16.973861694335938,
      "learning_rate": 2e-05,
      "loss": 2.5065,
      "step": 2
    },
    {
      "epoch": 0.00024155075585257353,
      "grad_norm": 17.152828216552734,
      "learning_rate": 3e-05,
      "loss": 2.5855,
      "step": 3
    },
    {
      "epoch": 0.00032206767447009804,
      "grad_norm": 11.791430473327637,
      "learning_rate": 4e-05,
      "loss": 2.206,
      "step": 4
    },
    {
      "epoch": 0.0004025845930876225,
      "grad_norm": 5.26390266418457,
      "learning_rate": 5e-05,
      "loss": 2.1781,
      "step": 5
    },
    {
      "epoch": 0.00048310151170514705,
      "grad_norm": 4.636106967926025,
      "learning_rate": 6e-05,
      "loss": 1.9751,
      "step": 6
    },
    {
      "epoch": 0.0005636184303226716,
      "grad_norm": 2.583982229232788,
      "learning_rate": 7e-05,
      "loss": 2.0084,
      "step": 7
    },
    {
      "epoch": 0.0006441353489401961,
      "grad_norm": 2.6073713302612305,
      "learning_rate": 8e-05,
      "loss": 2.003,
      "step": 8
    },
    {
      "epoch": 0.0007246522675577206,
      "grad_norm": 1.6990159749984741,
      "learning_rate": 9e-05,
      "loss": 2.0454,
      "step": 9
    },
    {
      "epoch": 0.000805169186175245,
      "grad_norm": 1.1776007413864136,
      "learning_rate": 0.0001,
      "loss": 1.8358,
      "step": 10
    },
    {
      "epoch": 0.0008856861047927696,
      "grad_norm": 1.0957061052322388,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.822,
      "step": 11
    },
    {
      "epoch": 0.0009662030234102941,
      "grad_norm": 1.2326781749725342,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.87,
      "step": 12
    },
    {
      "epoch": 0.0010467199420278186,
      "grad_norm": 0.7951018214225769,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.7797,
      "step": 13
    },
    {
      "epoch": 0.0011272368606453432,
      "grad_norm": 1.000949501991272,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7187,
      "step": 14
    },
    {
      "epoch": 0.0012077537792628676,
      "grad_norm": 0.6804490685462952,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.6691,
      "step": 15
    },
    {
      "epoch": 0.0012882706978803921,
      "grad_norm": 0.8919732570648193,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.7062,
      "step": 16
    },
    {
      "epoch": 0.0013687876164979165,
      "grad_norm": 0.5915566086769104,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.4411,
      "step": 17
    },
    {
      "epoch": 0.001449304535115441,
      "grad_norm": 0.8211526870727539,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.5822,
      "step": 18
    },
    {
      "epoch": 0.0015298214537329657,
      "grad_norm": 0.6463562846183777,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.5998,
      "step": 19
    },
    {
      "epoch": 0.00161033837235049,
      "grad_norm": 0.6516017317771912,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.6094,
      "step": 20
    },
    {
      "epoch": 0.0016908552909680147,
      "grad_norm": 1.0889999866485596,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.6938,
      "step": 21
    },
    {
      "epoch": 0.0017713722095855393,
      "grad_norm": 0.6314936280250549,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.4876,
      "step": 22
    },
    {
      "epoch": 0.0018518891282030636,
      "grad_norm": 0.6983410716056824,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.5488,
      "step": 23
    },
    {
      "epoch": 0.0019324060468205882,
      "grad_norm": 0.7183996438980103,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5917,
      "step": 24
    },
    {
      "epoch": 0.0020129229654381126,
      "grad_norm": 0.8171032667160034,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.5731,
      "step": 25
    },
    {
      "epoch": 0.002093439884055637,
      "grad_norm": 0.6705768704414368,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.5631,
      "step": 26
    },
    {
      "epoch": 0.0021739568026731618,
      "grad_norm": 0.6940917372703552,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.5664,
      "step": 27
    },
    {
      "epoch": 0.0022544737212906864,
      "grad_norm": 0.6975890398025513,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.5293,
      "step": 28
    },
    {
      "epoch": 0.0023349906399082105,
      "grad_norm": 0.7544741034507751,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4832,
      "step": 29
    },
    {
      "epoch": 0.002415507558525735,
      "grad_norm": 0.7494301199913025,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.7355,
      "step": 30
    },
    {
      "epoch": 0.0024960244771432597,
      "grad_norm": 0.8572993278503418,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.4665,
      "step": 31
    },
    {
      "epoch": 0.0025765413957607843,
      "grad_norm": 0.9226846694946289,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.3918,
      "step": 32
    },
    {
      "epoch": 0.002657058314378309,
      "grad_norm": 0.8625328540802002,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.6576,
      "step": 33
    },
    {
      "epoch": 0.002737575232995833,
      "grad_norm": 0.9232624769210815,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.4668,
      "step": 34
    },
    {
      "epoch": 0.0028180921516133576,
      "grad_norm": 0.8604220747947693,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.676,
      "step": 35
    },
    {
      "epoch": 0.002898609070230882,
      "grad_norm": 0.7628800272941589,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.4841,
      "step": 36
    },
    {
      "epoch": 0.002979125988848407,
      "grad_norm": 0.8315993547439575,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.5544,
      "step": 37
    },
    {
      "epoch": 0.0030596429074659314,
      "grad_norm": 0.7245994806289673,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.3446,
      "step": 38
    },
    {
      "epoch": 0.003140159826083456,
      "grad_norm": 1.0671409368515015,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.5982,
      "step": 39
    },
    {
      "epoch": 0.00322067674470098,
      "grad_norm": 0.7829718589782715,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.5017,
      "step": 40
    },
    {
      "epoch": 0.0033011936633185047,
      "grad_norm": 1.0271023511886597,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.6895,
      "step": 41
    },
    {
      "epoch": 0.0033817105819360293,
      "grad_norm": 0.9041717052459717,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.5579,
      "step": 42
    },
    {
      "epoch": 0.003462227500553554,
      "grad_norm": 0.9417299032211304,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.6506,
      "step": 43
    },
    {
      "epoch": 0.0035427444191710785,
      "grad_norm": 1.0171841382980347,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.8189,
      "step": 44
    },
    {
      "epoch": 0.0036232613377886027,
      "grad_norm": 1.0186662673950195,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.7005,
      "step": 45
    },
    {
      "epoch": 0.0037037782564061273,
      "grad_norm": 0.8959439992904663,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.2864,
      "step": 46
    },
    {
      "epoch": 0.003784295175023652,
      "grad_norm": 1.2057873010635376,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.7118,
      "step": 47
    },
    {
      "epoch": 0.0038648120936411764,
      "grad_norm": 1.2957358360290527,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7732,
      "step": 48
    },
    {
      "epoch": 0.003945329012258701,
      "grad_norm": 1.743603229522705,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.8185,
      "step": 49
    },
    {
      "epoch": 0.004025845930876225,
      "grad_norm": 1.515619158744812,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.9238,
      "step": 50
    },
    {
      "epoch": 0.004025845930876225,
      "eval_loss": 1.6345586776733398,
      "eval_runtime": 1570.1183,
      "eval_samples_per_second": 13.323,
      "eval_steps_per_second": 3.331,
      "step": 50
    },
    {
      "epoch": 0.00410636284949375,
      "grad_norm": 0.7655407190322876,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.3046,
      "step": 51
    },
    {
      "epoch": 0.004186879768111274,
      "grad_norm": 0.7856895327568054,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.6683,
      "step": 52
    },
    {
      "epoch": 0.0042673966867287985,
      "grad_norm": 0.7081140279769897,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.4311,
      "step": 53
    },
    {
      "epoch": 0.0043479136053463235,
      "grad_norm": 0.42009517550468445,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.4882,
      "step": 54
    },
    {
      "epoch": 0.004428430523963848,
      "grad_norm": 0.43536660075187683,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.4099,
      "step": 55
    },
    {
      "epoch": 0.004508947442581373,
      "grad_norm": 0.6052523851394653,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.4157,
      "step": 56
    },
    {
      "epoch": 0.004589464361198897,
      "grad_norm": 0.5873731374740601,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.5053,
      "step": 57
    },
    {
      "epoch": 0.004669981279816421,
      "grad_norm": 0.4847113788127899,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.4136,
      "step": 58
    },
    {
      "epoch": 0.004750498198433946,
      "grad_norm": 0.45475682616233826,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.385,
      "step": 59
    },
    {
      "epoch": 0.00483101511705147,
      "grad_norm": 0.5306957364082336,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.4937,
      "step": 60
    },
    {
      "epoch": 0.004911532035668995,
      "grad_norm": 0.5260341167449951,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3361,
      "step": 61
    },
    {
      "epoch": 0.004992048954286519,
      "grad_norm": 0.45000162720680237,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.3935,
      "step": 62
    },
    {
      "epoch": 0.0050725658729040436,
      "grad_norm": 0.5670515894889832,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.4097,
      "step": 63
    },
    {
      "epoch": 0.005153082791521569,
      "grad_norm": 0.555814802646637,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.4479,
      "step": 64
    },
    {
      "epoch": 0.005233599710139093,
      "grad_norm": 0.5043533444404602,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.4273,
      "step": 65
    },
    {
      "epoch": 0.005314116628756618,
      "grad_norm": 0.46356257796287537,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.3734,
      "step": 66
    },
    {
      "epoch": 0.005394633547374142,
      "grad_norm": 0.46080517768859863,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.4529,
      "step": 67
    },
    {
      "epoch": 0.005475150465991666,
      "grad_norm": 0.5072758793830872,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.4547,
      "step": 68
    },
    {
      "epoch": 0.005555667384609191,
      "grad_norm": 0.48776936531066895,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.3558,
      "step": 69
    },
    {
      "epoch": 0.005636184303226715,
      "grad_norm": 0.4939619302749634,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2648,
      "step": 70
    },
    {
      "epoch": 0.00571670122184424,
      "grad_norm": 0.5072360038757324,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.5307,
      "step": 71
    },
    {
      "epoch": 0.005797218140461764,
      "grad_norm": 0.6055448651313782,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.4612,
      "step": 72
    },
    {
      "epoch": 0.0058777350590792895,
      "grad_norm": 0.5122414827346802,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.4895,
      "step": 73
    },
    {
      "epoch": 0.005958251977696814,
      "grad_norm": 0.5090658068656921,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.3695,
      "step": 74
    },
    {
      "epoch": 0.006038768896314338,
      "grad_norm": 0.5476226210594177,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.4367,
      "step": 75
    },
    {
      "epoch": 0.006119285814931863,
      "grad_norm": 0.5305289030075073,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.3727,
      "step": 76
    },
    {
      "epoch": 0.006199802733549387,
      "grad_norm": 0.663529098033905,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.4814,
      "step": 77
    },
    {
      "epoch": 0.006280319652166912,
      "grad_norm": 0.6056848764419556,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.3346,
      "step": 78
    },
    {
      "epoch": 0.006360836570784436,
      "grad_norm": 0.6445757150650024,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.4986,
      "step": 79
    },
    {
      "epoch": 0.00644135348940196,
      "grad_norm": 0.6453158259391785,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.5582,
      "step": 80
    },
    {
      "epoch": 0.006521870408019485,
      "grad_norm": 0.6675869226455688,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.5507,
      "step": 81
    },
    {
      "epoch": 0.0066023873266370095,
      "grad_norm": 0.719948947429657,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.3881,
      "step": 82
    },
    {
      "epoch": 0.0066829042452545345,
      "grad_norm": 0.6834545135498047,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.5265,
      "step": 83
    },
    {
      "epoch": 0.006763421163872059,
      "grad_norm": 0.6420490145683289,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.4441,
      "step": 84
    },
    {
      "epoch": 0.006843938082489583,
      "grad_norm": 0.6377096772193909,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.6071,
      "step": 85
    },
    {
      "epoch": 0.006924455001107108,
      "grad_norm": 0.671746551990509,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.428,
      "step": 86
    },
    {
      "epoch": 0.007004971919724632,
      "grad_norm": 0.9008675813674927,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.3436,
      "step": 87
    },
    {
      "epoch": 0.007085488838342157,
      "grad_norm": 0.828833818435669,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.6059,
      "step": 88
    },
    {
      "epoch": 0.007166005756959681,
      "grad_norm": 0.640192985534668,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.4773,
      "step": 89
    },
    {
      "epoch": 0.007246522675577205,
      "grad_norm": 0.7338127493858337,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.4091,
      "step": 90
    },
    {
      "epoch": 0.00732703959419473,
      "grad_norm": 0.7946495413780212,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.3328,
      "step": 91
    },
    {
      "epoch": 0.0074075565128122545,
      "grad_norm": 0.8608148694038391,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.4283,
      "step": 92
    },
    {
      "epoch": 0.0074880734314297795,
      "grad_norm": 0.9165239930152893,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.5422,
      "step": 93
    },
    {
      "epoch": 0.007568590350047304,
      "grad_norm": 0.883380115032196,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.4067,
      "step": 94
    },
    {
      "epoch": 0.007649107268664828,
      "grad_norm": 0.9385941624641418,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.4757,
      "step": 95
    },
    {
      "epoch": 0.007729624187282353,
      "grad_norm": 1.201176404953003,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.8454,
      "step": 96
    },
    {
      "epoch": 0.007810141105899877,
      "grad_norm": 1.1753710508346558,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.7505,
      "step": 97
    },
    {
      "epoch": 0.007890658024517402,
      "grad_norm": 1.1829088926315308,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.6695,
      "step": 98
    },
    {
      "epoch": 0.007971174943134927,
      "grad_norm": 1.2344779968261719,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.7969,
      "step": 99
    },
    {
      "epoch": 0.00805169186175245,
      "grad_norm": 1.8585081100463867,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.351,
      "step": 100
    },
    {
      "epoch": 0.00805169186175245,
      "eval_loss": 1.5454622507095337,
      "eval_runtime": 1568.5572,
      "eval_samples_per_second": 13.336,
      "eval_steps_per_second": 3.334,
      "step": 100
    },
    {
      "epoch": 0.008132208780369975,
      "grad_norm": 0.4332025945186615,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.3323,
      "step": 101
    },
    {
      "epoch": 0.0082127256989875,
      "grad_norm": 0.5667193531990051,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.4548,
      "step": 102
    },
    {
      "epoch": 0.008293242617605024,
      "grad_norm": 0.4632430970668793,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.3655,
      "step": 103
    },
    {
      "epoch": 0.008373759536222549,
      "grad_norm": 0.4448387622833252,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.354,
      "step": 104
    },
    {
      "epoch": 0.008454276454840074,
      "grad_norm": 0.44413015246391296,
      "learning_rate": 5e-05,
      "loss": 1.2979,
      "step": 105
    },
    {
      "epoch": 0.008534793373457597,
      "grad_norm": 0.4363125264644623,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.2965,
      "step": 106
    },
    {
      "epoch": 0.008615310292075122,
      "grad_norm": 0.3793621361255646,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.429,
      "step": 107
    },
    {
      "epoch": 0.008695827210692647,
      "grad_norm": 0.4537980258464813,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.4519,
      "step": 108
    },
    {
      "epoch": 0.008776344129310172,
      "grad_norm": 0.43880966305732727,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.2921,
      "step": 109
    },
    {
      "epoch": 0.008856861047927695,
      "grad_norm": 0.4098110795021057,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.4163,
      "step": 110
    },
    {
      "epoch": 0.00893737796654522,
      "grad_norm": 0.42833250761032104,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.4617,
      "step": 111
    },
    {
      "epoch": 0.009017894885162745,
      "grad_norm": 0.44120481610298157,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.5578,
      "step": 112
    },
    {
      "epoch": 0.009098411803780269,
      "grad_norm": 0.4496973752975464,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.4641,
      "step": 113
    },
    {
      "epoch": 0.009178928722397794,
      "grad_norm": 0.4154663681983948,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.4246,
      "step": 114
    },
    {
      "epoch": 0.009259445641015319,
      "grad_norm": 0.5077388882637024,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.4113,
      "step": 115
    },
    {
      "epoch": 0.009339962559632842,
      "grad_norm": 0.41621333360671997,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.2711,
      "step": 116
    },
    {
      "epoch": 0.009420479478250367,
      "grad_norm": 0.4518488943576813,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.5033,
      "step": 117
    },
    {
      "epoch": 0.009500996396867892,
      "grad_norm": 0.5049459934234619,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.384,
      "step": 118
    },
    {
      "epoch": 0.009581513315485417,
      "grad_norm": 0.46755704283714294,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.3947,
      "step": 119
    },
    {
      "epoch": 0.00966203023410294,
      "grad_norm": 0.45540207624435425,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.3884,
      "step": 120
    },
    {
      "epoch": 0.009742547152720465,
      "grad_norm": 0.558189332485199,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.3281,
      "step": 121
    },
    {
      "epoch": 0.00982306407133799,
      "grad_norm": 0.5871676802635193,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.3694,
      "step": 122
    },
    {
      "epoch": 0.009903580989955514,
      "grad_norm": 0.5026249885559082,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.3705,
      "step": 123
    },
    {
      "epoch": 0.009984097908573039,
      "grad_norm": 0.5479567646980286,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.5545,
      "step": 124
    },
    {
      "epoch": 0.010064614827190564,
      "grad_norm": 0.49582353234291077,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.3612,
      "step": 125
    },
    {
      "epoch": 0.010145131745808087,
      "grad_norm": 0.5378618240356445,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.2243,
      "step": 126
    },
    {
      "epoch": 0.010225648664425612,
      "grad_norm": 0.6336896419525146,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.4806,
      "step": 127
    },
    {
      "epoch": 0.010306165583043137,
      "grad_norm": 0.5256307125091553,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.3563,
      "step": 128
    },
    {
      "epoch": 0.010386682501660662,
      "grad_norm": 0.736548900604248,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.4266,
      "step": 129
    },
    {
      "epoch": 0.010467199420278185,
      "grad_norm": 0.7321350574493408,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.4342,
      "step": 130
    },
    {
      "epoch": 0.01054771633889571,
      "grad_norm": 0.6737896203994751,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.5055,
      "step": 131
    },
    {
      "epoch": 0.010628233257513236,
      "grad_norm": 0.6772146821022034,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.6421,
      "step": 132
    },
    {
      "epoch": 0.010708750176130759,
      "grad_norm": 0.6847913265228271,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.4066,
      "step": 133
    },
    {
      "epoch": 0.010789267094748284,
      "grad_norm": 0.5601797699928284,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.4815,
      "step": 134
    },
    {
      "epoch": 0.010869784013365809,
      "grad_norm": 0.6792698502540588,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.5305,
      "step": 135
    },
    {
      "epoch": 0.010950300931983332,
      "grad_norm": 0.6913775205612183,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.499,
      "step": 136
    },
    {
      "epoch": 0.011030817850600857,
      "grad_norm": 0.7182140946388245,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.4599,
      "step": 137
    },
    {
      "epoch": 0.011111334769218382,
      "grad_norm": 0.6974215507507324,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.3921,
      "step": 138
    },
    {
      "epoch": 0.011191851687835907,
      "grad_norm": 0.8547173142433167,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.666,
      "step": 139
    },
    {
      "epoch": 0.01127236860645343,
      "grad_norm": 0.6126853823661804,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.3573,
      "step": 140
    },
    {
      "epoch": 0.011352885525070956,
      "grad_norm": 0.7265337705612183,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.3835,
      "step": 141
    },
    {
      "epoch": 0.01143340244368848,
      "grad_norm": 0.9371582269668579,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.7809,
      "step": 142
    },
    {
      "epoch": 0.011513919362306004,
      "grad_norm": 0.9845908284187317,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.5367,
      "step": 143
    },
    {
      "epoch": 0.011594436280923529,
      "grad_norm": 0.8650178909301758,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.4944,
      "step": 144
    },
    {
      "epoch": 0.011674953199541054,
      "grad_norm": 0.871677577495575,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.4172,
      "step": 145
    },
    {
      "epoch": 0.011755470118158579,
      "grad_norm": 0.8507685661315918,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.4916,
      "step": 146
    },
    {
      "epoch": 0.011835987036776102,
      "grad_norm": 0.9453696012496948,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.5359,
      "step": 147
    },
    {
      "epoch": 0.011916503955393627,
      "grad_norm": 1.0529489517211914,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.4942,
      "step": 148
    },
    {
      "epoch": 0.011997020874011152,
      "grad_norm": 0.9472283124923706,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.4193,
      "step": 149
    },
    {
      "epoch": 0.012077537792628676,
      "grad_norm": 1.4350203275680542,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.7319,
      "step": 150
    },
    {
      "epoch": 0.012077537792628676,
      "eval_loss": 1.4884361028671265,
      "eval_runtime": 1571.76,
      "eval_samples_per_second": 13.309,
      "eval_steps_per_second": 3.327,
      "step": 150
    },
    {
      "epoch": 0.0121580547112462,
      "grad_norm": 0.27087754011154175,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.2021,
      "step": 151
    },
    {
      "epoch": 0.012238571629863726,
      "grad_norm": 0.40103864669799805,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.3914,
      "step": 152
    },
    {
      "epoch": 0.012319088548481249,
      "grad_norm": 0.35810038447380066,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.4224,
      "step": 153
    },
    {
      "epoch": 0.012399605467098774,
      "grad_norm": 0.3255632519721985,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.3623,
      "step": 154
    },
    {
      "epoch": 0.012480122385716299,
      "grad_norm": 0.3383626341819763,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.4203,
      "step": 155
    },
    {
      "epoch": 0.012560639304333824,
      "grad_norm": 0.3385162651538849,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.3529,
      "step": 156
    },
    {
      "epoch": 0.012641156222951347,
      "grad_norm": 0.3744180202484131,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.4757,
      "step": 157
    },
    {
      "epoch": 0.012721673141568872,
      "grad_norm": 0.4350076913833618,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.3825,
      "step": 158
    },
    {
      "epoch": 0.012802190060186397,
      "grad_norm": 0.3727683126926422,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.2683,
      "step": 159
    },
    {
      "epoch": 0.01288270697880392,
      "grad_norm": 0.3879694938659668,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.285,
      "step": 160
    },
    {
      "epoch": 0.012963223897421446,
      "grad_norm": 0.3567706346511841,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.2847,
      "step": 161
    },
    {
      "epoch": 0.01304374081603897,
      "grad_norm": 0.40727657079696655,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.395,
      "step": 162
    },
    {
      "epoch": 0.013124257734656494,
      "grad_norm": 0.4111592769622803,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.3364,
      "step": 163
    },
    {
      "epoch": 0.013204774653274019,
      "grad_norm": 0.4039963483810425,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.4121,
      "step": 164
    },
    {
      "epoch": 0.013285291571891544,
      "grad_norm": 0.4668547511100769,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.3704,
      "step": 165
    },
    {
      "epoch": 0.013365808490509069,
      "grad_norm": 0.44965946674346924,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.4967,
      "step": 166
    },
    {
      "epoch": 0.013446325409126592,
      "grad_norm": 0.45821622014045715,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.3827,
      "step": 167
    },
    {
      "epoch": 0.013526842327744117,
      "grad_norm": 0.47117525339126587,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.4171,
      "step": 168
    },
    {
      "epoch": 0.013607359246361642,
      "grad_norm": 0.5134897232055664,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.4732,
      "step": 169
    },
    {
      "epoch": 0.013687876164979166,
      "grad_norm": 0.4456486105918884,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.3477,
      "step": 170
    },
    {
      "epoch": 0.01376839308359669,
      "grad_norm": 0.46276599168777466,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.2921,
      "step": 171
    },
    {
      "epoch": 0.013848910002214216,
      "grad_norm": 0.439720094203949,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.4475,
      "step": 172
    },
    {
      "epoch": 0.013929426920831739,
      "grad_norm": 0.4510144293308258,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.4766,
      "step": 173
    },
    {
      "epoch": 0.014009943839449264,
      "grad_norm": 0.5530790090560913,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.4134,
      "step": 174
    },
    {
      "epoch": 0.014090460758066789,
      "grad_norm": 0.5448698401451111,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.3896,
      "step": 175
    },
    {
      "epoch": 0.014170977676684314,
      "grad_norm": 0.4997592866420746,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.4161,
      "step": 176
    },
    {
      "epoch": 0.014251494595301837,
      "grad_norm": 0.5189532041549683,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.5577,
      "step": 177
    },
    {
      "epoch": 0.014332011513919362,
      "grad_norm": 0.5439527034759521,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.3212,
      "step": 178
    },
    {
      "epoch": 0.014412528432536887,
      "grad_norm": 0.7192681431770325,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.5677,
      "step": 179
    },
    {
      "epoch": 0.01449304535115441,
      "grad_norm": 0.6316661834716797,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.3937,
      "step": 180
    },
    {
      "epoch": 0.014573562269771936,
      "grad_norm": 0.655982255935669,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.5644,
      "step": 181
    },
    {
      "epoch": 0.01465407918838946,
      "grad_norm": 0.6037099957466125,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.3178,
      "step": 182
    },
    {
      "epoch": 0.014734596107006984,
      "grad_norm": 0.5587989687919617,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.4235,
      "step": 183
    },
    {
      "epoch": 0.014815113025624509,
      "grad_norm": 0.608555793762207,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.4717,
      "step": 184
    },
    {
      "epoch": 0.014895629944242034,
      "grad_norm": 0.6629654169082642,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.4587,
      "step": 185
    },
    {
      "epoch": 0.014976146862859559,
      "grad_norm": 0.6644917130470276,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.1795,
      "step": 186
    },
    {
      "epoch": 0.015056663781477082,
      "grad_norm": 0.7392715215682983,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.4153,
      "step": 187
    },
    {
      "epoch": 0.015137180700094607,
      "grad_norm": 0.6920585632324219,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.334,
      "step": 188
    },
    {
      "epoch": 0.015217697618712132,
      "grad_norm": 0.7683362364768982,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.5024,
      "step": 189
    },
    {
      "epoch": 0.015298214537329656,
      "grad_norm": 0.7444142699241638,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.3491,
      "step": 190
    },
    {
      "epoch": 0.01537873145594718,
      "grad_norm": 0.8493619561195374,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.6089,
      "step": 191
    },
    {
      "epoch": 0.015459248374564706,
      "grad_norm": 0.8487809896469116,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.4754,
      "step": 192
    },
    {
      "epoch": 0.01553976529318223,
      "grad_norm": 1.0723888874053955,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.563,
      "step": 193
    },
    {
      "epoch": 0.015620282211799754,
      "grad_norm": 1.0452873706817627,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.673,
      "step": 194
    },
    {
      "epoch": 0.01570079913041728,
      "grad_norm": 0.9166924953460693,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.4996,
      "step": 195
    },
    {
      "epoch": 0.015781316049034804,
      "grad_norm": 0.8552730083465576,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.2976,
      "step": 196
    },
    {
      "epoch": 0.01586183296765233,
      "grad_norm": 1.1161834001541138,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.656,
      "step": 197
    },
    {
      "epoch": 0.015942349886269854,
      "grad_norm": 1.1046738624572754,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.7262,
      "step": 198
    },
    {
      "epoch": 0.016022866804887376,
      "grad_norm": 1.2741045951843262,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.682,
      "step": 199
    },
    {
      "epoch": 0.0161033837235049,
      "grad_norm": 1.4451305866241455,
      "learning_rate": 0.0,
      "loss": 1.8149,
      "step": 200
    },
    {
      "epoch": 0.0161033837235049,
      "eval_loss": 1.4893763065338135,
      "eval_runtime": 1570.7867,
      "eval_samples_per_second": 13.317,
      "eval_steps_per_second": 3.33,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7847343411822592e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}