{
  "best_metric": 0.0580073706805706,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.20865936358894105,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010432968179447052,
      "grad_norm": 0.23914818465709686,
      "learning_rate": 1e-05,
      "loss": 0.1992,
      "step": 1
    },
    {
      "epoch": 0.0010432968179447052,
      "eval_loss": 0.11727960407733917,
      "eval_runtime": 216.4332,
      "eval_samples_per_second": 7.457,
      "eval_steps_per_second": 1.867,
      "step": 1
    },
    {
      "epoch": 0.0020865936358894104,
      "grad_norm": 0.22359982132911682,
      "learning_rate": 2e-05,
      "loss": 0.2043,
      "step": 2
    },
    {
      "epoch": 0.003129890453834116,
      "grad_norm": 0.22367903590202332,
      "learning_rate": 3e-05,
      "loss": 0.2031,
      "step": 3
    },
    {
      "epoch": 0.004173187271778821,
      "grad_norm": 0.22789771854877472,
      "learning_rate": 4e-05,
      "loss": 0.1938,
      "step": 4
    },
    {
      "epoch": 0.005216484089723527,
      "grad_norm": 0.18350918591022491,
      "learning_rate": 5e-05,
      "loss": 0.1959,
      "step": 5
    },
    {
      "epoch": 0.006259780907668232,
      "grad_norm": 0.15268462896347046,
      "learning_rate": 6e-05,
      "loss": 0.176,
      "step": 6
    },
    {
      "epoch": 0.007303077725612937,
      "grad_norm": 0.11760733276605606,
      "learning_rate": 7e-05,
      "loss": 0.1842,
      "step": 7
    },
    {
      "epoch": 0.008346374543557642,
      "grad_norm": 0.13854435086250305,
      "learning_rate": 8e-05,
      "loss": 0.1785,
      "step": 8
    },
    {
      "epoch": 0.009389671361502348,
      "grad_norm": 0.12135294824838638,
      "learning_rate": 9e-05,
      "loss": 0.1789,
      "step": 9
    },
    {
      "epoch": 0.010432968179447054,
      "grad_norm": 0.11645561456680298,
      "learning_rate": 0.0001,
      "loss": 0.1787,
      "step": 10
    },
    {
      "epoch": 0.011476264997391758,
      "grad_norm": 0.11218249052762985,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.1876,
      "step": 11
    },
    {
      "epoch": 0.012519561815336464,
      "grad_norm": 0.11002285033464432,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.1776,
      "step": 12
    },
    {
      "epoch": 0.013562858633281168,
      "grad_norm": 0.09712035208940506,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.1724,
      "step": 13
    },
    {
      "epoch": 0.014606155451225874,
      "grad_norm": 0.09712543338537216,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.1565,
      "step": 14
    },
    {
      "epoch": 0.01564945226917058,
      "grad_norm": 0.08914125710725784,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.1728,
      "step": 15
    },
    {
      "epoch": 0.016692749087115284,
      "grad_norm": 0.09943269193172455,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.1694,
      "step": 16
    },
    {
      "epoch": 0.01773604590505999,
      "grad_norm": 0.08599051088094711,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.1616,
      "step": 17
    },
    {
      "epoch": 0.018779342723004695,
      "grad_norm": 0.09019957482814789,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.1418,
      "step": 18
    },
    {
      "epoch": 0.0198226395409494,
      "grad_norm": 0.08000475913286209,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.0351,
      "step": 19
    },
    {
      "epoch": 0.020865936358894107,
      "grad_norm": 0.17777150869369507,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0196,
      "step": 20
    },
    {
      "epoch": 0.02190923317683881,
      "grad_norm": 0.08581084758043289,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0168,
      "step": 21
    },
    {
      "epoch": 0.022952529994783515,
      "grad_norm": 0.07062641531229019,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.0122,
      "step": 22
    },
    {
      "epoch": 0.023995826812728223,
      "grad_norm": 0.08069050312042236,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.0087,
      "step": 23
    },
    {
      "epoch": 0.025039123630672927,
      "grad_norm": 0.1165061667561531,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0036,
      "step": 24
    },
    {
      "epoch": 0.02608242044861763,
      "grad_norm": 0.0456419438123703,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0012,
      "step": 25
    },
    {
      "epoch": 0.027125717266562335,
      "grad_norm": 0.05539556220173836,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0011,
      "step": 26
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 0.05253702029585838,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0014,
      "step": 27
    },
    {
      "epoch": 0.029212310902451747,
      "grad_norm": 0.019506292417645454,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0002,
      "step": 28
    },
    {
      "epoch": 0.03025560772039645,
      "grad_norm": 0.039464663714170456,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0004,
      "step": 29
    },
    {
      "epoch": 0.03129890453834116,
      "grad_norm": 0.010064296424388885,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0002,
      "step": 30
    },
    {
      "epoch": 0.03234220135628586,
      "grad_norm": 0.0039469231851398945,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.0001,
      "step": 31
    },
    {
      "epoch": 0.03338549817423057,
      "grad_norm": 0.007584957871586084,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0001,
      "step": 32
    },
    {
      "epoch": 0.03442879499217527,
      "grad_norm": 0.1555258333683014,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0011,
      "step": 33
    },
    {
      "epoch": 0.03547209181011998,
      "grad_norm": 0.030517704784870148,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0002,
      "step": 34
    },
    {
      "epoch": 0.036515388628064686,
      "grad_norm": 0.011871867813169956,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.0001,
      "step": 35
    },
    {
      "epoch": 0.03755868544600939,
      "grad_norm": 0.03730761259794235,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0003,
      "step": 36
    },
    {
      "epoch": 0.038601982263954095,
      "grad_norm": 0.08780539035797119,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.0004,
      "step": 37
    },
    {
      "epoch": 0.0396452790818988,
      "grad_norm": 0.0026147824246436357,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0001,
      "step": 38
    },
    {
      "epoch": 0.0406885758998435,
      "grad_norm": 0.013097596354782581,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.0002,
      "step": 39
    },
    {
      "epoch": 0.041731872717788214,
      "grad_norm": 0.05856119468808174,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.001,
      "step": 40
    },
    {
      "epoch": 0.04277516953573292,
      "grad_norm": 0.013078159652650356,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0002,
      "step": 41
    },
    {
      "epoch": 0.04381846635367762,
      "grad_norm": 0.0028536240570247173,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0001,
      "step": 42
    },
    {
      "epoch": 0.044861763171622326,
      "grad_norm": 0.0016919774934649467,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.04590505998956703,
      "grad_norm": 0.013510230928659439,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0001,
      "step": 44
    },
    {
      "epoch": 0.046948356807511735,
      "grad_norm": 0.0022312134969979525,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0001,
      "step": 45
    },
    {
      "epoch": 0.047991653625456446,
      "grad_norm": 0.014168251305818558,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0001,
      "step": 46
    },
    {
      "epoch": 0.04903495044340115,
      "grad_norm": 0.040536049753427505,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0002,
      "step": 47
    },
    {
      "epoch": 0.050078247261345854,
      "grad_norm": 0.08585729449987411,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.001,
      "step": 48
    },
    {
      "epoch": 0.05112154407929056,
      "grad_norm": 0.033363815397024155,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0003,
      "step": 49
    },
    {
      "epoch": 0.05216484089723526,
      "grad_norm": 0.0332404226064682,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0002,
      "step": 50
    },
    {
      "epoch": 0.05216484089723526,
      "eval_loss": 0.10003285109996796,
      "eval_runtime": 218.4334,
      "eval_samples_per_second": 7.389,
      "eval_steps_per_second": 1.85,
      "step": 50
    },
    {
      "epoch": 0.053208137715179966,
      "grad_norm": 1.912048578262329,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.2644,
      "step": 51
    },
    {
      "epoch": 0.05425143453312467,
      "grad_norm": 0.31019654870033264,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.2083,
      "step": 52
    },
    {
      "epoch": 0.05529473135106938,
      "grad_norm": 0.3941453993320465,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.1986,
      "step": 53
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 0.2588464021682739,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.1762,
      "step": 54
    },
    {
      "epoch": 0.05738132498695879,
      "grad_norm": 0.13643278181552887,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.1667,
      "step": 55
    },
    {
      "epoch": 0.058424621804903494,
      "grad_norm": 0.15387576818466187,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.1781,
      "step": 56
    },
    {
      "epoch": 0.0594679186228482,
      "grad_norm": 0.11620111763477325,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.1701,
      "step": 57
    },
    {
      "epoch": 0.0605112154407929,
      "grad_norm": 0.09808052331209183,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.1657,
      "step": 58
    },
    {
      "epoch": 0.06155451225873761,
      "grad_norm": 0.08006507158279419,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.1639,
      "step": 59
    },
    {
      "epoch": 0.06259780907668232,
      "grad_norm": 0.08802084624767303,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.1589,
      "step": 60
    },
    {
      "epoch": 0.06364110589462701,
      "grad_norm": 0.09210347384214401,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.1664,
      "step": 61
    },
    {
      "epoch": 0.06468440271257173,
      "grad_norm": 0.08319375663995743,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.1637,
      "step": 62
    },
    {
      "epoch": 0.06572769953051644,
      "grad_norm": 0.08420167863368988,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.1545,
      "step": 63
    },
    {
      "epoch": 0.06677099634846113,
      "grad_norm": 0.08467259258031845,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.1595,
      "step": 64
    },
    {
      "epoch": 0.06781429316640585,
      "grad_norm": 0.08317424356937408,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.1634,
      "step": 65
    },
    {
      "epoch": 0.06885758998435054,
      "grad_norm": 0.08032103627920151,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.1567,
      "step": 66
    },
    {
      "epoch": 0.06990088680229525,
      "grad_norm": 0.07455036044120789,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1462,
      "step": 67
    },
    {
      "epoch": 0.07094418362023996,
      "grad_norm": 0.08996720612049103,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.1371,
      "step": 68
    },
    {
      "epoch": 0.07198748043818466,
      "grad_norm": 0.10640854388475418,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0177,
      "step": 69
    },
    {
      "epoch": 0.07303077725612937,
      "grad_norm": 0.07385112345218658,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0091,
      "step": 70
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.06649098545312881,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0063,
      "step": 71
    },
    {
      "epoch": 0.07511737089201878,
      "grad_norm": 0.05004905164241791,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.003,
      "step": 72
    },
    {
      "epoch": 0.07616066770996348,
      "grad_norm": 0.026123173534870148,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0016,
      "step": 73
    },
    {
      "epoch": 0.07720396452790819,
      "grad_norm": 0.016001999378204346,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0003,
      "step": 74
    },
    {
      "epoch": 0.0782472613458529,
      "grad_norm": 0.014428561553359032,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0007,
      "step": 75
    },
    {
      "epoch": 0.0792905581637976,
      "grad_norm": 0.00947485025972128,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0003,
      "step": 76
    },
    {
      "epoch": 0.08033385498174231,
      "grad_norm": 0.03772318735718727,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0005,
      "step": 77
    },
    {
      "epoch": 0.081377151799687,
      "grad_norm": 0.07924376428127289,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0004,
      "step": 78
    },
    {
      "epoch": 0.08242044861763172,
      "grad_norm": 0.023915281519293785,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0002,
      "step": 79
    },
    {
      "epoch": 0.08346374543557643,
      "grad_norm": 0.008038005791604519,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0002,
      "step": 80
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 0.004151181783527136,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0001,
      "step": 81
    },
    {
      "epoch": 0.08555033907146584,
      "grad_norm": 0.009893108159303665,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0001,
      "step": 82
    },
    {
      "epoch": 0.08659363588941053,
      "grad_norm": 0.2031213641166687,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0035,
      "step": 83
    },
    {
      "epoch": 0.08763693270735524,
      "grad_norm": 0.022429514676332474,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0003,
      "step": 84
    },
    {
      "epoch": 0.08868022952529994,
      "grad_norm": 0.014127877540886402,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0001,
      "step": 85
    },
    {
      "epoch": 0.08972352634324465,
      "grad_norm": 0.008402218110859394,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0002,
      "step": 86
    },
    {
      "epoch": 0.09076682316118936,
      "grad_norm": 0.03237013518810272,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0004,
      "step": 87
    },
    {
      "epoch": 0.09181011997913406,
      "grad_norm": 0.05123713240027428,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0016,
      "step": 88
    },
    {
      "epoch": 0.09285341679707877,
      "grad_norm": 0.17595256865024567,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0025,
      "step": 89
    },
    {
      "epoch": 0.09389671361502347,
      "grad_norm": 0.05363395810127258,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.002,
      "step": 90
    },
    {
      "epoch": 0.09494001043296818,
      "grad_norm": 0.01816258393228054,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0011,
      "step": 91
    },
    {
      "epoch": 0.09598330725091289,
      "grad_norm": 0.019630957394838333,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0004,
      "step": 92
    },
    {
      "epoch": 0.09702660406885759,
      "grad_norm": 0.005481023341417313,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0001,
      "step": 93
    },
    {
      "epoch": 0.0980699008868023,
      "grad_norm": 0.006372000090777874,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0001,
      "step": 94
    },
    {
      "epoch": 0.099113197704747,
      "grad_norm": 0.01990051008760929,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0001,
      "step": 95
    },
    {
      "epoch": 0.10015649452269171,
      "grad_norm": 0.01231410726904869,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0001,
      "step": 96
    },
    {
      "epoch": 0.1011997913406364,
      "grad_norm": 0.19465799629688263,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0025,
      "step": 97
    },
    {
      "epoch": 0.10224308815858112,
      "grad_norm": 0.10165459662675858,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0002,
      "step": 98
    },
    {
      "epoch": 0.10328638497652583,
      "grad_norm": 0.067677341401577,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0011,
      "step": 99
    },
    {
      "epoch": 0.10432968179447052,
      "grad_norm": 0.07877156883478165,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0021,
      "step": 100
    },
    {
      "epoch": 0.10432968179447052,
      "eval_loss": 0.08003425598144531,
      "eval_runtime": 218.9154,
      "eval_samples_per_second": 7.373,
      "eval_steps_per_second": 1.845,
      "step": 100
    },
    {
      "epoch": 0.10537297861241524,
      "grad_norm": 0.6338253021240234,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.2009,
      "step": 101
    },
    {
      "epoch": 0.10641627543035993,
      "grad_norm": 0.21986190974712372,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.1852,
      "step": 102
    },
    {
      "epoch": 0.10745957224830464,
      "grad_norm": 0.143763467669487,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.1617,
      "step": 103
    },
    {
      "epoch": 0.10850286906624934,
      "grad_norm": 0.1620103269815445,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.1669,
      "step": 104
    },
    {
      "epoch": 0.10954616588419405,
      "grad_norm": 0.13760386407375336,
      "learning_rate": 5e-05,
      "loss": 0.1767,
      "step": 105
    },
    {
      "epoch": 0.11058946270213876,
      "grad_norm": 0.11622602492570877,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.1608,
      "step": 106
    },
    {
      "epoch": 0.11163275952008346,
      "grad_norm": 0.0973973497748375,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.1645,
      "step": 107
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 0.08213253319263458,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.1742,
      "step": 108
    },
    {
      "epoch": 0.11371935315597287,
      "grad_norm": 0.07610011100769043,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1638,
      "step": 109
    },
    {
      "epoch": 0.11476264997391758,
      "grad_norm": 0.07191264629364014,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1544,
      "step": 110
    },
    {
      "epoch": 0.11580594679186229,
      "grad_norm": 0.08377819508314133,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.1713,
      "step": 111
    },
    {
      "epoch": 0.11684924360980699,
      "grad_norm": 0.07115169614553452,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.1629,
      "step": 112
    },
    {
      "epoch": 0.1178925404277517,
      "grad_norm": 0.08253469318151474,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.1748,
      "step": 113
    },
    {
      "epoch": 0.1189358372456964,
      "grad_norm": 0.07538585364818573,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.1561,
      "step": 114
    },
    {
      "epoch": 0.11997913406364111,
      "grad_norm": 0.07405910640954971,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.1533,
      "step": 115
    },
    {
      "epoch": 0.1210224308815858,
      "grad_norm": 0.07342270016670227,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1576,
      "step": 116
    },
    {
      "epoch": 0.12206572769953052,
      "grad_norm": 0.07734149694442749,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.1512,
      "step": 117
    },
    {
      "epoch": 0.12310902451747523,
      "grad_norm": 0.06752760708332062,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1471,
      "step": 118
    },
    {
      "epoch": 0.12415232133541992,
      "grad_norm": 0.07015020400285721,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0705,
      "step": 119
    },
    {
      "epoch": 0.12519561815336464,
      "grad_norm": 0.05140012875199318,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0111,
      "step": 120
    },
    {
      "epoch": 0.12623891497130935,
      "grad_norm": 0.05692361295223236,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0093,
      "step": 121
    },
    {
      "epoch": 0.12728221178925403,
      "grad_norm": 0.05468055605888367,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0089,
      "step": 122
    },
    {
      "epoch": 0.12832550860719874,
      "grad_norm": 0.052533503621816635,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0078,
      "step": 123
    },
    {
      "epoch": 0.12936880542514345,
      "grad_norm": 0.06854812055826187,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0076,
      "step": 124
    },
    {
      "epoch": 0.13041210224308816,
      "grad_norm": 0.06454082578420639,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0061,
      "step": 125
    },
    {
      "epoch": 0.13145539906103287,
      "grad_norm": 0.048144612461328506,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0039,
      "step": 126
    },
    {
      "epoch": 0.13249869587897756,
      "grad_norm": 0.044483482837677,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.003,
      "step": 127
    },
    {
      "epoch": 0.13354199269692227,
      "grad_norm": 0.04744779318571091,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0026,
      "step": 128
    },
    {
      "epoch": 0.13458528951486698,
      "grad_norm": 0.07754551619291306,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.002,
      "step": 129
    },
    {
      "epoch": 0.1356285863328117,
      "grad_norm": 0.032896995544433594,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0018,
      "step": 130
    },
    {
      "epoch": 0.1366718831507564,
      "grad_norm": 0.07949315011501312,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.0017,
      "step": 131
    },
    {
      "epoch": 0.13771517996870108,
      "grad_norm": 0.014896341599524021,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0005,
      "step": 132
    },
    {
      "epoch": 0.1387584767866458,
      "grad_norm": 0.010353720746934414,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0004,
      "step": 133
    },
    {
      "epoch": 0.1398017736045905,
      "grad_norm": 0.06870342791080475,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0004,
      "step": 134
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 0.011892154812812805,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0003,
      "step": 135
    },
    {
      "epoch": 0.14188836724047993,
      "grad_norm": 0.045861780643463135,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0005,
      "step": 136
    },
    {
      "epoch": 0.1429316640584246,
      "grad_norm": 0.017032982781529427,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0002,
      "step": 137
    },
    {
      "epoch": 0.14397496087636932,
      "grad_norm": 0.002508810255676508,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0001,
      "step": 138
    },
    {
      "epoch": 0.14501825769431403,
      "grad_norm": 0.004733174107968807,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0001,
      "step": 139
    },
    {
      "epoch": 0.14606155451225875,
      "grad_norm": 0.005658079404383898,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0002,
      "step": 140
    },
    {
      "epoch": 0.14710485133020346,
      "grad_norm": 0.039688147604465485,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0003,
      "step": 141
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.03600848838686943,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0003,
      "step": 142
    },
    {
      "epoch": 0.14919144496609285,
      "grad_norm": 0.0038012813311070204,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0001,
      "step": 143
    },
    {
      "epoch": 0.15023474178403756,
      "grad_norm": 0.161346435546875,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.001,
      "step": 144
    },
    {
      "epoch": 0.15127803860198227,
      "grad_norm": 0.002495797351002693,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0001,
      "step": 145
    },
    {
      "epoch": 0.15232133541992696,
      "grad_norm": 0.004729344043880701,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0002,
      "step": 146
    },
    {
      "epoch": 0.15336463223787167,
      "grad_norm": 0.0022545186802744865,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0001,
      "step": 147
    },
    {
      "epoch": 0.15440792905581638,
      "grad_norm": 0.010777679271996021,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0002,
      "step": 148
    },
    {
      "epoch": 0.1554512258737611,
      "grad_norm": 0.024113312363624573,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0007,
      "step": 149
    },
    {
      "epoch": 0.1564945226917058,
      "grad_norm": 0.06294465065002441,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0018,
      "step": 150
    },
    {
      "epoch": 0.1564945226917058,
      "eval_loss": 0.06094738468527794,
      "eval_runtime": 218.8009,
      "eval_samples_per_second": 7.377,
      "eval_steps_per_second": 1.846,
      "step": 150
    },
    {
      "epoch": 0.15753781950965048,
      "grad_norm": 0.11738583445549011,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.1669,
      "step": 151
    },
    {
      "epoch": 0.1585811163275952,
      "grad_norm": 0.10904942452907562,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.1526,
      "step": 152
    },
    {
      "epoch": 0.1596244131455399,
      "grad_norm": 0.10393431782722473,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.1767,
      "step": 153
    },
    {
      "epoch": 0.16066770996348462,
      "grad_norm": 0.1295202523469925,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.1632,
      "step": 154
    },
    {
      "epoch": 0.16171100678142933,
      "grad_norm": 0.09657377004623413,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.1487,
      "step": 155
    },
    {
      "epoch": 0.162754303599374,
      "grad_norm": 0.09321653097867966,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.1536,
      "step": 156
    },
    {
      "epoch": 0.16379760041731872,
      "grad_norm": 0.07935728132724762,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.153,
      "step": 157
    },
    {
      "epoch": 0.16484089723526343,
      "grad_norm": 0.0795266404747963,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.1669,
      "step": 158
    },
    {
      "epoch": 0.16588419405320814,
      "grad_norm": 0.07656994462013245,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.1672,
      "step": 159
    },
    {
      "epoch": 0.16692749087115286,
      "grad_norm": 0.07408581674098969,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.1547,
      "step": 160
    },
    {
      "epoch": 0.16797078768909754,
      "grad_norm": 0.07020696252584457,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.1451,
      "step": 161
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 0.07377953082323074,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1551,
      "step": 162
    },
    {
      "epoch": 0.17005738132498696,
      "grad_norm": 0.06756389141082764,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.1667,
      "step": 163
    },
    {
      "epoch": 0.17110067814293167,
      "grad_norm": 0.06751938164234161,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.1575,
      "step": 164
    },
    {
      "epoch": 0.17214397496087636,
      "grad_norm": 0.07463949173688889,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.166,
      "step": 165
    },
    {
      "epoch": 0.17318727177882107,
      "grad_norm": 0.06722015887498856,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.1574,
      "step": 166
    },
    {
      "epoch": 0.17423056859676578,
      "grad_norm": 0.07286033034324646,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.1608,
      "step": 167
    },
    {
      "epoch": 0.1752738654147105,
      "grad_norm": 0.06938737630844116,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.1598,
      "step": 168
    },
    {
      "epoch": 0.1763171622326552,
      "grad_norm": 0.06949499249458313,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.1588,
      "step": 169
    },
    {
      "epoch": 0.17736045905059988,
      "grad_norm": 0.0699697956442833,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0663,
      "step": 170
    },
    {
      "epoch": 0.1784037558685446,
      "grad_norm": 0.017542682588100433,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0018,
      "step": 171
    },
    {
      "epoch": 0.1794470526864893,
      "grad_norm": 0.024322470650076866,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0008,
      "step": 172
    },
    {
      "epoch": 0.18049034950443402,
      "grad_norm": 0.006017901003360748,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.0001,
      "step": 173
    },
    {
      "epoch": 0.18153364632237873,
      "grad_norm": 0.006720453500747681,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0002,
      "step": 174
    },
    {
      "epoch": 0.1825769431403234,
      "grad_norm": 0.010069251991808414,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0002,
      "step": 175
    },
    {
      "epoch": 0.18362023995826812,
      "grad_norm": 0.00938663724809885,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0002,
      "step": 176
    },
    {
      "epoch": 0.18466353677621283,
      "grad_norm": 0.015280010178685188,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0004,
      "step": 177
    },
    {
      "epoch": 0.18570683359415754,
      "grad_norm": 0.005021647084504366,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0001,
      "step": 178
    },
    {
      "epoch": 0.18675013041210226,
      "grad_norm": 0.003463650355115533,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0001,
      "step": 179
    },
    {
      "epoch": 0.18779342723004694,
      "grad_norm": 0.008023015223443508,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0002,
      "step": 180
    },
    {
      "epoch": 0.18883672404799165,
      "grad_norm": 0.0050609298050403595,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0001,
      "step": 181
    },
    {
      "epoch": 0.18988002086593636,
      "grad_norm": 0.006091528572142124,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0003,
      "step": 182
    },
    {
      "epoch": 0.19092331768388107,
      "grad_norm": 0.013220442458987236,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0005,
      "step": 183
    },
    {
      "epoch": 0.19196661450182578,
      "grad_norm": 0.01647050492465496,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0002,
      "step": 184
    },
    {
      "epoch": 0.19300991131977047,
      "grad_norm": 0.013951905071735382,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0004,
      "step": 185
    },
    {
      "epoch": 0.19405320813771518,
      "grad_norm": 0.02038080245256424,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0011,
      "step": 186
    },
    {
      "epoch": 0.1950965049556599,
      "grad_norm": 0.025439724326133728,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0002,
      "step": 187
    },
    {
      "epoch": 0.1961398017736046,
      "grad_norm": 0.013977092690765858,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0004,
      "step": 188
    },
    {
      "epoch": 0.19718309859154928,
      "grad_norm": 0.010392135940492153,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0002,
      "step": 189
    },
    {
      "epoch": 0.198226395409494,
      "grad_norm": 0.019125502556562424,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.001,
      "step": 190
    },
    {
      "epoch": 0.1992696922274387,
      "grad_norm": 0.002377947559580207,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0001,
      "step": 191
    },
    {
      "epoch": 0.20031298904538342,
      "grad_norm": 0.009925136342644691,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0002,
      "step": 192
    },
    {
      "epoch": 0.20135628586332813,
      "grad_norm": 0.0017528351163491607,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0001,
      "step": 193
    },
    {
      "epoch": 0.2023995826812728,
      "grad_norm": 0.0044202352873981,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0001,
      "step": 194
    },
    {
      "epoch": 0.20344287949921752,
      "grad_norm": 0.016982626169919968,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0005,
      "step": 195
    },
    {
      "epoch": 0.20448617631716223,
      "grad_norm": 0.016103088855743408,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0005,
      "step": 196
    },
    {
      "epoch": 0.20552947313510694,
      "grad_norm": 0.019755130633711815,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0005,
      "step": 197
    },
    {
      "epoch": 0.20657276995305165,
      "grad_norm": 0.046021267771720886,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0014,
      "step": 198
    },
    {
      "epoch": 0.20761606677099634,
      "grad_norm": 0.009208845905959606,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0003,
      "step": 199
    },
    {
      "epoch": 0.20865936358894105,
      "grad_norm": 0.1478404700756073,
      "learning_rate": 0.0,
      "loss": 0.0103,
      "step": 200
    },
    {
      "epoch": 0.20865936358894105,
      "eval_loss": 0.0580073706805706,
      "eval_runtime": 218.3839,
      "eval_samples_per_second": 7.391,
      "eval_steps_per_second": 1.85,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.2497169329527194e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}